SpecProof: tool descriptions scored ai.specproof/specproof-mcp

tools/list taken: 2026-11-02 (UTC)
From: Official MCP Registry
Connected to: https://mcp.specproof.ai/
Homepage: specproof.ai
Repository: github.com/ibouazizi/specproof.git
Scoring rules: v2
Removal: support@forecall.dev

Scores, issues and names only

This page shows how SpecProof (ai.specproof/specproof-mcp)'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/ai.specproof/specproof-mcp

Average score: 48.5 / 100Cloudy
Tools: 17
Near-identical descriptions: 0

Across the server

No server-wide issues.

Tools

get_spec_dependents

31 / 100Rain

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 3 / 25
Return value: 8 / 15
Constraints and side effects: 3 / 10
Examples: 0 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: spec_number, max_results.param_no_description
Minor
String arguments with no constraint or example: spec_number.loose_string_param

get_spec_references

33 / 100Rain

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 3 / 25
Return value: 8 / 15
Constraints and side effects: 0 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: spec_number, reference_type.param_no_description
Minor
String arguments with no constraint or example: spec_number.loose_string_param
Minor
No constraints, side effects, auth or rate limits described, and no annotations.no_constraints

get_most_referenced_specs

41 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 5 / 25
Return value: 8 / 15
Constraints and side effects: 3 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: doc_type, series, limit.param_no_description
Minor
No `required` list, so every argument is optional.no_required

get_spec_metadata

41 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 5 / 25
Return value: 8 / 15
Constraints and side effects: 3 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: spec_number, series, working_group, doc_class, limit.param_no_description
Minor
No `required` list, so every argument is optional.no_required

get_document_content

43 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 3 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: filename, page_range, section.param_no_description
Minor
String arguments with no constraint or example: filename.loose_string_param

get_relationship_graph

43 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 3 / 25
Return value: 15 / 15
Constraints and side effects: 0 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: spec_number, depth, reference_type.param_no_description
Minor
String arguments with no constraint or example: spec_number.loose_string_param
Minor
No constraints, side effects, auth or rate limits described, and no annotations.no_constraints

get_database_stats

46 / 100Cloudy

Purpose: 6 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 0 / 10

Major
The description only restates the name (6 words).restates_name
Major
The description is too short (6 words).too_short
Major
Says nothing about when to use it, or when not to.no_usage_context

list_documents

48 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 5 / 25
Return value: 8 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: doc_type, search_pattern, limit.param_no_description
Minor
No `required` list, so every argument is optional.no_required

get_rfc_lineage

50 / 100Cloudy

Purpose: 17 / 20
When to use: 10 / 20
Arguments: 3 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Arguments without a description: rfc.param_no_description
Minor
String arguments with no constraint or example: rfc.loose_string_param

get_series_overview

50 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 25 / 25
Return value: 8 / 15
Constraints and side effects: 0 / 10
Examples: 0 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Minor
No constraints, side effects, auth or rate limits described, and no annotations.no_constraints

semantic_search

50 / 100Cloudy

Purpose: 17 / 20
When to use: 0 / 20
Arguments: 3 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: query, max_results, similarity_threshold, index_type.param_no_description
Minor
String arguments with no constraint or example: query.loose_string_param

generate_tests

53 / 100Cloudy

Purpose: 20 / 20
When to use: 5 / 20
Arguments: 8 / 25
Return value: 8 / 15
Constraints and side effects: 7 / 10
Examples: 5 / 10

Major
Arguments without a description: requirement_id, target.param_no_description
Minor
Required identifiers whose description does not say where the value comes from: requirement_id. Name the tool or the place that returns it, or models look it up first.id_source_missing

search_specifications

53 / 100Cloudy

Purpose: 20 / 20
When to use: 0 / 20
Arguments: 3 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Says nothing about when to use it, or when not to.no_usage_context
Major
Arguments without a description: query, doc_type, spec_number, max_results.param_no_description
Minor
String arguments with no constraint or example: query.loose_string_param

build_cross_spec_suite

55 / 100Cloudy

Purpose: 17 / 20
When to use: 5 / 20
Arguments: 3 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Arguments without a description: spec_base, keyword, include_references, limit.param_no_description
Minor
String arguments with no constraint or example: spec_base, keyword.loose_string_param
Minor
The meaning of the boolean argument include_references is unclear.vague_boolean

diff_spec_versions

56 / 100Cloudy

Purpose: 20 / 20
When to use: 10 / 20
Arguments: 3 / 25
Return value: 8 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Arguments without a description: spec_base, from_version, to_version, obligation, limit.param_no_description
Minor
String arguments with no constraint or example: spec_base.loose_string_param

get_requirements

65 / 100Cloudy

Purpose: 20 / 20
When to use: 10 / 20
Arguments: 5 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Arguments without a description: spec_number, obligation, search, limit.param_no_description
Minor
No `required` list, so every argument is optional.no_required

get_schema_definitions

67 / 100Cloudy

Purpose: 17 / 20
When to use: 15 / 20
Arguments: 5 / 25
Return value: 15 / 15
Constraints and side effects: 10 / 10
Examples: 5 / 10

Major
Arguments without a description: name, spec_number, kind, limit.param_no_description
Minor
No `required` list, so every argument is optional.no_required

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