Forecall
Failure recordsDocs
All scored servers

TestGraph: tool descriptions scored io.github.BBCBasic/testgraph

tools/list taken
(UTC)
From
Official MCP Registry
Connected to
https://testgraph.21dle.co.uk/mcp-v2
Repository
github.com/BBCBasic/TestGraph
Scoring rules
v2
Removal
support@forecall.dev
Score this URL as it is today

Scores, issues and names only

This page shows how TestGraph (io.github.BBCBasic/testgraph)'s tool descriptions scored, the issues found and the names of its tools and parameters. The descriptions are the server's own: read them where the copy came from.

Forecall asked the URL this server lists in the official MCP Registry for its tools/list once, on the date above, without calling any tool. The server may have changed since.

servers/io.github.BBCBasic/testgraph
Average score
51.9 / 100Cloudy
Tools
37
Near-identical descriptions
4

Across the server

  • Minor
    37 tools. Above 25, models start to tell tools apart less well.many_tools
  • Minor
    The server's instructions are 6673 characters. Claude Code reads only the first 2,048 by default (Codex 0.154.0 reads them whole). Put what the server is for first.instructions_long

Tools whose descriptions are nearly the same

4 of 4 pairs shown, highest description similarity first.
ToolToolDescription similarityName similarity
list_root_subject_typeslist_child_subject_types0.860.60
correct_subject_factassert_location0.690.00
vocabulary_indexlist_root_subject_types0.660.00
vocabulary_indexlist_child_subject_types0.650.00

Tools

retire_type_relationship

31 / 100Rain

Purpose
17 / 20
When to use
0 / 20
Arguments
7 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: source_type, relationship, target_type, reason.param_no_description
  • Minor
    String arguments with no constraint or example: source_type, target_type.loose_string_param
  • Minor
    Says nothing about what it returns.no_return_info

resolve_subject_type

32 / 100Rain

Purpose
20 / 20
When to use
0 / 20
Arguments
5 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: term.param_no_description
  • Minor
    String arguments with no constraint or example: term.loose_string_param
  • Minor
    Says nothing about what it returns.no_return_info

fetch

34 / 100Rain

Purpose
17 / 20
When to use
0 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: id.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.id_source_missing

resolve_location_assertion

34 / 100Rain

Purpose
17 / 20
When to use
0 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: assertion_id, decision, rationale, user_approved, idempotency_key.param_no_description
  • Minor
    The description mentions none of its 3 or more arguments.params_not_in_description
  • Minor
    The meaning of the boolean argument user_approved is unclear.vague_boolean
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: assertion_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

reopen_subject_classification

36 / 100Rain

Purpose
14 / 20
When to use
5 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_id, trigger, reason, evidence, user_approved.param_no_description
  • Minor
    The meaning of the boolean argument user_approved is unclear.vague_boolean
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: subject_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

claim_deliberation

37 / 100Rain

Purpose
17 / 20
When to use
0 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: deliberation_id, source_model, idempotency_key.param_no_description
  • Minor
    The description mentions none of its 3 or more arguments.params_not_in_description
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: deliberation_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

get_subject_classification

39 / 100Rain

Purpose
17 / 20
When to use
5 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_id.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: subject_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

list_my_workflows

39 / 100Rain

Purpose
17 / 20
When to use
5 / 20
Arguments
7 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: limit.param_no_description
  • Minor
    No `required` list, so every argument is optional.no_required
  • Minor
    Says nothing about what it returns.no_return_info

get_location_assertions

41 / 100Cloudy

Purpose
17 / 20
When to use
0 / 20
Arguments
10 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: subject_id.param_no_description
  • Minor
    Required identifiers whose description does not say where the value comes from: subject_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

list_my_mcp_interactions

41 / 100Cloudy

Purpose
17 / 20
When to use
0 / 20
Arguments
7 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: limit.param_no_description
  • Minor
    No `required` list, so every argument is optional.no_required

get_deliberation

42 / 100Cloudy

Purpose
20 / 20
When to use
5 / 20
Arguments
7 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: id, canonical_key.param_no_description
  • Minor
    No `required` list, so every argument is optional.no_required
  • Minor
    Says nothing about what it returns.no_return_info

list_open_deliberations

42 / 100Cloudy

Purpose
20 / 20
When to use
0 / 20
Arguments
12 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: unclaimed_only, limit.param_no_description
  • Minor
    No `required` list, so every argument is optional.no_required
  • Minor
    The meaning of the boolean argument unclaimed_only is unclear.vague_boolean
  • Minor
    Says nothing about what it returns.no_return_info

record_resolution

44 / 100Cloudy

Purpose
20 / 20
When to use
5 / 20
Arguments
9 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: deliberation_id, resolution, rationale, accepted_contribution_ids, unresolved_points, user_approved, idempotency_key.param_no_description
  • Minor
    String arguments with no constraint or example: rationale.loose_string_param
  • Minor
    The meaning of the boolean argument user_approved is unclear.vague_boolean
  • Minor
    Says nothing about what it returns.no_return_info

set_review_visibility

44 / 100Cloudy

Purpose
17 / 20
When to use
0 / 20
Arguments
10 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Says nothing about when to use it, or when not to.no_usage_context
  • Major
    Arguments without a description: experience_id, visibility.param_no_description
  • Minor
    Required identifiers whose description does not say where the value comes from: experience_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

register_field

47 / 100Cloudy

Purpose
20 / 20
When to use
15 / 20
Arguments
5 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: canonical_name, json_schema, description, aliases, subject_types.param_no_description
  • Minor
    String arguments with no constraint or example: canonical_name, description.loose_string_param
  • Minor
    The description mentions none of its 3 or more arguments.params_not_in_description
  • Minor
    Says nothing about what it returns.no_return_info

submit_contribution

47 / 100Cloudy

Purpose
20 / 20
When to use
10 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: deliberation_id, contribution_type, content, evidence, confidence, unresolved_points, responds_to_contribution_ids, source_model, idempotency_key.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: deliberation_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

resolve_subject

48 / 100Cloudy

Purpose
17 / 20
When to use
10 / 20
Arguments
6 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
5 / 10
  • Major
    Arguments without a description: subject_type, canonical_key, name, identifier_value, identifier_key, limit.param_no_description
  • Minor
    String arguments with no constraint or example: subject_type.loose_string_param
  • Minor
    No `required` list, so every argument is optional.no_required
  • Minor
    Says nothing about what it returns.no_return_info

create_deliberation

52 / 100Cloudy

Purpose
20 / 20
When to use
5 / 20
Arguments
12 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
5 / 10
  • Major
    Arguments without a description: canonical_key, title, question, context, constraints, acceptance_criteria, idempotency_key.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info

delete_experience

52 / 100Cloudy

Purpose
17 / 20
When to use
15 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: id, delete_orphan_subject, confirm_deletion, idempotency_key.param_no_description
  • Minor
    The description mentions none of its 3 or more arguments.params_not_in_description
  • Minor
    The meaning of the boolean argument delete_orphan_subject is unclear.vague_boolean
  • Minor
    The meaning of the boolean argument confirm_deletion is unclear.vague_boolean
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.id_source_missing

register_subject_type_alias

52 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
5 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_type, alias.param_no_description
  • Minor
    String arguments with no constraint or example: subject_type, alias.loose_string_param
  • Minor
    Says nothing about what it returns.no_return_info

affirm_subject_classification

53 / 100Cloudy

Purpose
20 / 20
When to use
10 / 20
Arguments
13 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_id, reason, evidence, evidence_fingerprint.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: subject_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

list_reviews_by_visibility

57 / 100Cloudy

Purpose
20 / 20
When to use
10 / 20
Arguments
10 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: visibility.param_no_description

propose_subject_reclassification

57 / 100Cloudy

Purpose
20 / 20
When to use
15 / 20
Arguments
12 / 25
Return value
0 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_id, target_subject_type, reason, evidence, evidence_fingerprint.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info
  • Minor
    Required identifiers whose description does not say where the value comes from: subject_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

list_root_subject_types

58 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
4 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: limit, cursor, relationship.param_no_description
  • Minor
    Its description is nearly the same as list_child_subject_types's (similarity 0.86); only the names and schemas tell them apart. Say in this description when to use list_child_subject_types instead.confusable_pair
  • Minor
    Its description is nearly the same as vocabulary_index's (similarity 0.66); only the names and schemas tell them apart. Say in this description when to use vocabulary_index instead.confusable_pair
  • Minor
    String arguments with no constraint or example: cursor.loose_string_param
  • Minor
    No `required` list, so every argument is optional.no_required

list_child_subject_types

59 / 100Cloudy

Purpose
17 / 20
When to use
20 / 20
Arguments
8 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: parent, limit, cursor, relationship.param_no_description
  • Minor
    Its description is nearly the same as list_root_subject_types's (similarity 0.86); only the names and schemas tell them apart. Say in this description when to use list_root_subject_types instead.confusable_pair
  • Minor
    Its description is nearly the same as vocabulary_index's (similarity 0.65); only the names and schemas tell them apart. Say in this description when to use vocabulary_index instead.confusable_pair
  • Minor
    String arguments with no constraint or example: cursor.loose_string_param
  • Minor
    Required identifiers whose description does not say where the value comes from: parent. Name the tool or the place that returns it, or models look it up first.id_source_missing

set_type_relationship

59 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
7 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
5 / 10
  • Major
    Arguments without a description: source_type, relationship, target_type, peer_decision, peer_decision.decision, peer_decision.reason.param_no_description
  • Minor
    String arguments with no constraint or example: source_type, target_type.loose_string_param
  • Minor
    Says nothing about what it returns.no_return_info

assert_location

61 / 100Cloudy

Purpose
20 / 20
When to use
15 / 20
Arguments
9 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_id, predicate, object_place, object_place.subject_id, object_place.name, object_place.canonical_key, object_place.identifiers, object_place.place_kind, value, qualifiers, source, observed_at, valid_from, valid_to, visibility, idempotency_key.param_no_description
  • Minor
    Its description is nearly the same as correct_subject_fact's (similarity 0.69); only the names and schemas tell them apart. Say in this description when to use correct_subject_fact instead.confusable_pair
  • Minor
    String arguments with no constraint or example: object_place.name, object_place.canonical_key, object_place.place_kind.loose_string_param
  • Minor
    Required identifiers whose description does not say where the value comes from: subject_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

search

61 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
7 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: query, subject_type, include_related, limit.param_no_description
  • Minor
    String arguments with no constraint or example: subject_type.loose_string_param
  • Minor
    No `required` list, so every argument is optional.no_required
  • Minor
    The meaning of the boolean argument include_related is unclear.vague_boolean

resolve_subject_hierarchy

62 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
10 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
5 / 10
  • Major
    Arguments without a description: terms, peer_decisions, peer_decisions[].term, peer_decisions[].decision, peer_decisions[].existing_type, peer_decisions[].reason, peer_decisions[].term, peer_decisions[].decision, peer_decisions[].reason.param_no_description
  • Minor
    Says nothing about what it returns.no_return_info

correct_subject_fact

64 / 100Cloudy

Purpose
20 / 20
When to use
15 / 20
Arguments
12 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_id, field_root, expected_value, corrected_value, evidence_sources, reason, idempotency_key.param_no_description
  • Minor
    Its description is nearly the same as assert_location's (similarity 0.69); only the names and schemas tell them apart. Say in this description when to use assert_location instead.confusable_pair

get_subject_type_path

64 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
10 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Major
    Arguments without a description: subject_type, relationship.param_no_description

save_assessment

64 / 100Cloudy

Purpose
20 / 20
When to use
20 / 20
Arguments
7 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
0 / 10
  • Major
    Arguments without a description: experience_id, assessment_type, evidence, analysis, conclusion, confidence, source_model, idempotency_key.param_no_description
  • Minor
    String arguments with no constraint or example: assessment_type, conclusion, source_model.loose_string_param
  • Minor
    Required identifiers whose description does not say where the value comes from: experience_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

get_induction

68 / 100Cloudy

Purpose
17 / 20
When to use
15 / 20
Arguments
22 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Minor
    No `required` list, so every argument is optional.no_required

vocabulary_index

69 / 100Cloudy

Purpose
17 / 20
When to use
20 / 20
Arguments
25 / 25
Return value
0 / 15
Constraints and side effects
7 / 10
Examples
0 / 10
  • Minor
    Its description is nearly the same as list_root_subject_types's (similarity 0.66); only the names and schemas tell them apart. Say in this description when to use list_root_subject_types instead.confusable_pair
  • Minor
    Its description is nearly the same as list_child_subject_types's (similarity 0.65); only the names and schemas tell them apart. Say in this description when to use list_child_subject_types instead.confusable_pair
  • Minor
    Says nothing about what it returns.no_return_info

get_server_info

74 / 100Clear

Purpose
20 / 20
When to use
15 / 20
Arguments
25 / 25
Return value
7 / 15
Constraints and side effects
7 / 10
Examples
0 / 10

No issues.

save_experience

77 / 100Clear

Purpose
20 / 20
When to use
20 / 20
Arguments
10 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
10 / 10
  • Major
    Arguments without a description: subject_type, subject_name, canonical_key, source_model, identifiers, subject_attributes, subject_provenance, subject_enrichment_check.status, subject_enrichment_check.sources, subject_enrichment_check.attempts, subject_enrichment_check.reason, subject_enrichment_check.candidate_identities, collection_assessment.status, collection_assessment.collection_id, collection_assessment.manifest_revision, collection_assessment.refresh_manifest, collection_assessment.collection_name, collection_assessment.collection_type, collection_assessment.directory_url, collection_assessment.discovered_count, collection_assessment.submitted_member_refs, collection_assessment.source_manifest.coverage_method, collection_assessment.source_manifest.declared_source_count, collection_assessment.source_manifest.source_pages, collection_assessment.source_manifest.source_pages[].url, collection_assessment.source_manifest.source_pages[].source_kind, collection_assessment.source_manifest.source_pages[].sequence, collection_assessment.source_manifest.source_pages[].member_refs, collection_assessment.source_manifest.source_pages[].next_url, collection_assessment.source_manifest.source_pages[].terminal, collection_assessment.source_manifest.discovery_queries, collection_assessment.source_manifest.exhaustion_evidence, collection_assessment.source_manifest.unresolved_source_urls, collection_assessment.evidence_sources, collection_assessment.attempts, collection_assessment.reason, collection_assessment.candidate_collections, collection_assessment.checked_at, headline, summary, raw_text, structured_data, experienced_at, subject_context.subjects, subject_context.subjects[].ref, subject_context.subjects[].subject_type, subject_context.subjects[].name, subject_context.subjects[].canonical_key, subject_context.subjects[].identifiers, subject_context.subjects[].attributes, subject_context.subjects[].provenance, subject_context.relationships, subject_context.relationships[].source_ref, subject_context.relationships[].relationship, subject_context.relationships[].target_ref, subject_context.relationships[].provenance, visibility, user_approved, idempotency_key.param_no_description
  • Minor
    The description is long (884 words). It helps selection but costs steps and tokens.too_long
  • Minor
    String arguments with no constraint or example: subject_type, subject_name, canonical_key, headline, summary, subject_context.subjects[].subject_type, subject_context.subjects[].name, subject_context.subjects[].canonical_key, subject_context.relationships[].source_ref, subject_context.relationships[].relationship, subject_context.relationships[].target_ref.loose_string_param
  • Minor
    The meaning of the boolean argument collection_assessment.refresh_manifest is unclear.vague_boolean
  • Minor
    The meaning of the boolean argument collection_assessment.source_manifest.source_pages[].terminal is unclear.vague_boolean
  • Minor
    The meaning of the boolean argument user_approved is unclear.vague_boolean

enrich_subject

78 / 100Clear

Purpose
20 / 20
When to use
20 / 20
Arguments
11 / 25
Return value
7 / 15
Constraints and side effects
10 / 10
Examples
10 / 10
  • Major
    Arguments without a description: subject_type, canonical_key, source_model, identifiers, attributes, provenance, subject_context.subjects, subject_context.subjects[].ref, subject_context.subjects[].subject_type, subject_context.subjects[].name, subject_context.subjects[].canonical_key, subject_context.subjects[].identifiers, subject_context.subjects[].attributes, subject_context.subjects[].provenance, subject_context.relationships, subject_context.relationships[].source_ref, subject_context.relationships[].relationship, subject_context.relationships[].target_ref, subject_context.relationships[].provenance, idempotency_key, subject_enrichment_check.status, subject_enrichment_check.sources, subject_enrichment_check.attempts, subject_enrichment_check.reason, subject_enrichment_check.candidate_identities, collection_assessment.status, collection_assessment.collection_id, collection_assessment.manifest_revision, collection_assessment.refresh_manifest, collection_assessment.collection_name, collection_assessment.collection_type, collection_assessment.directory_url, collection_assessment.discovered_count, collection_assessment.submitted_member_refs, collection_assessment.source_manifest.coverage_method, collection_assessment.source_manifest.declared_source_count, collection_assessment.source_manifest.source_pages, collection_assessment.source_manifest.source_pages[].url, collection_assessment.source_manifest.source_pages[].source_kind, collection_assessment.source_manifest.source_pages[].sequence, collection_assessment.source_manifest.source_pages[].member_refs, collection_assessment.source_manifest.source_pages[].next_url, collection_assessment.source_manifest.source_pages[].terminal, collection_assessment.source_manifest.discovery_queries, collection_assessment.source_manifest.exhaustion_evidence, collection_assessment.source_manifest.unresolved_source_urls, collection_assessment.evidence_sources, collection_assessment.attempts, collection_assessment.reason, collection_assessment.candidate_collections, collection_assessment.checked_at.param_no_description
  • Minor
    The description is long (536 words). It helps selection but costs steps and tokens.too_long
  • Minor
    String arguments with no constraint or example: subject_type, canonical_key, subject_context.subjects[].subject_type, subject_context.subjects[].name, subject_context.subjects[].canonical_key, subject_context.relationships[].source_ref, subject_context.relationships[].relationship, subject_context.relationships[].target_ref.loose_string_param
  • Minor
    The meaning of the boolean argument collection_assessment.refresh_manifest is unclear.vague_boolean
  • Minor
    The meaning of the boolean argument collection_assessment.source_manifest.source_pages[].terminal is unclear.vague_boolean

What static scoring cannot tell

This score reads only the text of each description and schema: it says what is written, not what a model will do. Short tools whose names already say what they do, such as browser_close, score low here even when models use them well, and in our measurements current models chose the right tool in one step even from one-line descriptions, as long as the names and schemas differed. What the text cannot show, such as what happens over several steps and whether an added sentence helps or misleads, is what an evaluation measures, on the Pro and Team plans.

Is your server listed here and you would rather it were not? Email support@forecall.dev, and we will take it off within 7 days.

All scored servers