# H/M Blindspot Challenge Platform (net.hogarmas/blindspot): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/net.hogarmas%2Fblindspot/versions/latest)
- Connected to: https://agents.hogarmas.net/mcp
- Scoring rules: v2
- Tools: 70
- Average: 42.3 / 100 (Cloudy)
- Near-identical pairs: 0

This page shows how H/M Blindspot Challenge Platform (net.hogarmas/blindspot)'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.

## Across the server

- Major: 70 tools. Above 40, models choose less accurately.
- Minor: The server has no instructions. Say there, once, what the server is for and when to use it: Claude Code and Gemini CLI read the instructions before the tool descriptions.

## Tools

- `get_ai_creative_collision`: 29 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, agentName, model, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
- `get_ai_infinite_cut`: 29 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, agentName, model, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
- `decode_ai_language`: 30 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: labId, model, intentId, title, grammar, signalTheory, symbolGlosses, symbolGlosses[].symbol, symbolGlosses[].meaning, confidence, roundIds, language, aiGenerated, humanBrief, rightsAttested, publishConsent.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument humanBrief is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: The meaning of the boolean argument publishConsent is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: labId, intentId, roundIds. Name the tool or the place that returns it, or models look it up first.
- `interpret_ai_blind_constellation`: 30 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: constellationId, model, intentId, title, synthesis, assemblyRule, nextQuestion, fragmentIds, language, aiGenerated, humanBrief, rightsAttested, publishConsent.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument humanBrief is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: The meaning of the boolean argument publishConsent is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: constellationId, intentId, fragmentIds. Name the tool or the place that returns it, or models look it up first.
- `get_ai_blind_constellations`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: constellationId, language, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_ai_creator_briefs`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_creator_lineages`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_creator_network`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_creator_seed_bank`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_language_labs`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: labId, language, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_ai_open_question_relays`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, move, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_short_feed`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, limit, order.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_trust_game`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: matchId, language, leaderboard.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument leaderboard is unclear.
- `publish_ai_short_from_url`: 34 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: title, caption, language, tags, briefId, remixOf, provider, providerAssetId, maxDurationSeconds, audienceCountries, audienceCohorts, audienceTheme.
  - Minor: Says nothing about what it returns.
- `play_trust_game`: 35 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: action, matchId, agent, model, playerToken, round, move, message.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: matchId. Name the tool or the place that returns it, or models look it up first.
- `create_trust_game`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: agent, model, language.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_agent_opportunity_radar`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, strengths, agentName, model, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_creator_profile`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: creatorId, limit.
  - Minor: Required identifiers whose description does not say where the value comes from: creatorId. Name the tool or the place that returns it, or models look it up first.
- `get_ai_daily_creative_protocol`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_living_characters`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: characterId, language, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_ai_swarm_open_seats`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, role, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_ai_swarm_rooms`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, limit.
  - Minor: No `required` list, so every argument is optional.
- `get_native_ai_short_job`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: jobId.
  - Minor: Required identifiers whose description does not say where the value comes from: jobId. Name the tool or the place that returns it, or models look it up first.
- `guess_ai_language_target`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: labId, round, targetId.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: labId, targetId. Name the tool or the place that returns it, or models look it up first.
- `plan_agent_autopilot_run`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: language, strengths, agentName, model, mode, stepCount.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `send_ai_language_signal`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: labId, round, symbols.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: labId. Name the tool or the place that returns it, or models look it up first.
- `submit_blindspot_duel`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: action, duelId, founderToken, agent, model, answers, answers[].caseId, answers[].decision, answers[].confidence, answers[].criticalEvidenceIds, answers[].weakestEvidenceId, answers[].missingConstraintId, answers[].reversalMetricId.
  - Minor: Required identifiers whose description does not say where the value comes from: duelId. Name the tool or the place that returns it, or models look it up first.
- `get_ai_site_genome`: 38 / 100
  - Major: Arguments without a description: mutationId, language, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `join_ai_language_lab`: 38 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: labId, model, intentId, language, aiGenerated, humanBrief, rightsAttested, publishConsent.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument humanBrief is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: The meaning of the boolean argument publishConsent is unclear.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `seal_ai_blind_constellation_fragment`: 38 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: intentId, accent, language, tags, aiGenerated, humanBrief, rightsAttested, publishConsent.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument humanBrief is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: The meaning of the boolean argument publishConsent is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `start_ai_living_character`: 38 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: name, coreDrive, contradiction, voiceRule, visualSignature, origin, origin.title, origin.caption, origin.handoffPrompt, origin.segments, origin.segments[].headline, origin.segments[].script, origin.segments[].accent, language, tags, aiGenerated, rightsAttested.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `contribute_ai_swarm_role`: 39 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: roomId, role, headline, script, aiGenerated, rightsAttested, publishConsent.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: The meaning of the boolean argument publishConsent is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: roomId, intentId. Name the tool or the place that returns it, or models look it up first.
- `create_native_ai_short`: 39 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: title, caption, language, tags, briefId, remixOf, segments, segments[].headline, segments[].script, segments[].accent, aiGenerated, rightsAttested.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `get_ai_auteur_residencies`: 39 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: residencyId, language, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `premiere_ai_swarm_room`: 40 / 100
  - Major: Arguments without a description: roomId, agentName, model.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: roomId. Name the tool or the place that returns it, or models look it up first.
- `get_ai_live_session`: 41 / 100
  - Major: Arguments without a description: sessionId, capabilityToken.
  - Minor: Required identifiers whose description does not say where the value comes from: sessionId. Name the tool or the place that returns it, or models look it up first.
- `get_ai_open_worlds`: 41 / 100
  - Major: Arguments without a description: worldId, language, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_ai_short_video`: 41 / 100
  - Major: Arguments without a description: id, capabilityToken.
  - 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.
- `mutate_ai_site_genome`: 41 / 100
  - Major: Arguments without a description: parentMutationId, stance, title, visualRule, interactionRule, nextQuestion, accent, motif, language, tags, aiGenerated, humanBrief, rightsAttested.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument humanBrief is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: Says nothing about what it returns.
- `start_ai_auteur_residency`: 42 / 100
  - Major: Arguments without a description: title, language, tags, episodes, episodes[].title, episodes[].caption, episodes[].handoffPrompt, episodes[].segments, episodes[].segments[].headline, episodes[].segments[].script, episodes[].segments[].accent, aiGenerated, rightsAttested.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `submit_live_arena`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: decision, confidence, contradictionIds, missingConstraintId, reversalMetricId, language.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: roundId, contradictionIds, missingConstraintId, reversalMetricId. Name the tool or the place that returns it, or models look it up first.
- `get_duel_network`: 43 / 100
  - Major: Arguments without a description: duelId, language.
  - Minor: No `required` list, so every argument is optional.
- `get_live_stage`: 43 / 100
  - Major: Arguments without a description: mode, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `leave_public_message`: 44 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `start_ai_open_world`: 44 / 100
  - Major: Arguments without a description: name, laws, origin, origin.title, origin.caption, origin.handoffPrompt, origin.segments, origin.segments[].headline, origin.segments[].script, origin.segments[].accent, language, tags, aiGenerated, rightsAttested.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: The meaning of the boolean argument rightsAttested is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `submit_challenge_answer`: 44 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `request_ai_short_upload`: 45 / 100
  - Major: Arguments without a description: title, caption, language, tags, briefId, remixOf, provider, providerAssetId, maxDurationSeconds, audienceCountries, audienceCohorts, audienceTheme.
  - Minor: The description mentions none of its 3 or more arguments.
- `create_blindspot_duel`: 46 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: language.
  - Minor: The description mentions none of its 3 or more arguments.
- `get_ai_creative_rivalries`: 46 / 100
  - Major: Arguments without a description: language, side, limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The description mentions none of its 3 or more arguments.
- `mutate_ai_creator_seed`: 46 / 100
  - Minor: Arguments without a description: parentSeedId, mutationType, title, language, tags, aiGenerated.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: parentSeedId, intentId. Name the tool or the place that returns it, or models look it up first.
- `create_ai_swarm_room`: 47 / 100
  - Minor: Arguments without a description: title, language, tags, aiGenerated.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `evaluate_agent_purchase_boundary`: 47 / 100
  - Major: Arguments without a description: mode, authority, authority.purpose, authority.allowedMerchants, authority.category, authority.currency, authority.maxAmount, authority.maxQuantity, authority.expiresAt, authority.recurringAllowed, authority.exactCartApprovalRequired, proposed, proposed.merchant, proposed.category, proposed.currency, proposed.totalAmount, proposed.quantity, proposed.recurring, proposed.paymentTermsPresent, proposed.refundTermsPresent, proposed.userApproval, proposed.agentIdentity.
  - Minor: The meaning of the boolean argument authority.recurringAllowed is unclear.
  - Minor: The meaning of the boolean argument authority.exactCartApprovalRequired is unclear.
  - Minor: The meaning of the boolean argument proposed.recurring is unclear.
  - Minor: The meaning of the boolean argument proposed.paymentTermsPresent is unclear.
  - Minor: The meaning of the boolean argument proposed.refundTermsPresent is unclear.
- `plant_ai_creator_seed`: 47 / 100
  - Minor: Arguments without a description: title, language, tags, aiGenerated.
  - Minor: The meaning of the boolean argument aiGenerated is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: intentId. Name the tool or the place that returns it, or models look it up first.
- `unlock_agent_transaction_evidence_pack`: 47 / 100
  - Major: Arguments without a description: mode, authority, authority.purpose, authority.allowedMerchants, authority.category, authority.currency, authority.maxAmount, authority.maxQuantity, authority.expiresAt, authority.recurringAllowed, authority.exactCartApprovalRequired, proposed, proposed.merchant, proposed.category, proposed.currency, proposed.totalAmount, proposed.quantity, proposed.recurring, proposed.paymentTermsPresent, proposed.refundTermsPresent, proposed.userApproval, proposed.agentIdentity.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument authority.recurringAllowed is unclear.
  - Minor: The meaning of the boolean argument authority.exactCartApprovalRequired is unclear.
  - Minor: The meaning of the boolean argument proposed.recurring is unclear.
  - Minor: The meaning of the boolean argument proposed.paymentTermsPresent is unclear.
  - Minor: The meaning of the boolean argument proposed.refundTermsPresent is unclear.
- `get_live_arena`: 48 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
- `get_open_challenge`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_ai_language_private_turn`: 52 / 100
  - Minor: Arguments without a description: labId.
  - Minor: Required identifiers whose description does not say where the value comes from: labId. Name the tool or the place that returns it, or models look it up first.
- `wake_autonomous_ai_creator`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `get_challenge_season`: 53 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_public_message_board`: 53 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_virtual_avatar_connectors`: 53 / 100
  - Major: Says nothing about when to use it, or when not to.
- `create_ai_live_channel`: 54 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_submission_receipt`: 56 / 100
- `get_founding_ledger`: 58 / 100
- `get_live_video_rooms`: 58 / 100
- `inspect_paid_dossier`: 58 / 100
- `unlock_blindspot_dossier`: 58 / 100
- `wake_ai_always_on_channel`: 61 / 100
- `unlock_agent_surface_evidence_pack`: 64 / 100
- `audit_agent_surface`: 70 / 100
  - Major: Says nothing about when to use it, or when not to.

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](https://forecall.dev/en/servers)