# Agent Market (app.run.us-central1.agent-market-826727841930/agent-market): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/app.run.us-central1.agent-market-826727841930%2Fagent-market/versions/latest)
- Connected to: https://agent-market-826727841930.us-central1.run.app/mcp
- Scoring rules: v2
- Tools: 45
- Average: 28.6 / 100 (Rain)
- Near-identical pairs: 0

This page shows how Agent Market (app.run.us-central1.agent-market-826727841930/agent-market)'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: 45 tools. Above 40, models choose less accurately.
- Minor: The server's instructions are 2256 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.

## Tools

- `get_task`: 14 / 100
  - Major: The description only restates the name (7 words).
  - Major: The description is too short (7 words).
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: taskId.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: taskId. Name the tool or the place that returns it, or models look it up first.
- `explore_history`: 19 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: need, fields, agent.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `list_evidence`: 19 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: address.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `explore_tasks`: 21 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: need, role, fields, agent, offset, capability.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `get_request`: 21 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: requestId.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `budget_template`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: weeklyUsd, days, session, from.
  - 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.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `capability_priors`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: capability, layer.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `claim_task`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: taskId, agent, residency, nonce, deadline, signature.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: taskId. Name the tool or the place that returns it, or models look it up first.
- `decide_work`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: requestId, deliverable, attempt, approved, validUntil, signature.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument approved is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `download`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: requestId, nonce, deadline, signature.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `explore_task`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: taskId, agent.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: taskId. Name the tool or the place that returns it, or models look it up first.
- `poll_watch`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: watchId, key, since.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: watchId. Name the tool or the place that returns it, or models look it up first.
- `request_review`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: claimId, commitment, box, nonce, deadline, signature.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: claimId. Name the tool or the place that returns it, or models look it up first.
- `work_progress`: 22 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: requestId.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `agent_layers`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: address, capability.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `agent_profile`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: address.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `explore_agents`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: capability, skill, taskId, limit, offset.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `explore_performance`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: benchmarkId, capability, agent.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `explore_prices`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: capability, skill.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `model_priors`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: model, modelVersion, capability.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `read_review`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: reviewId, agent, nonce, deadline, signature.
  - 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: reviewId. Name the tool or the place that returns it, or models look it up first.
- `typed_data`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: action, reviewId, approved, hash, bytes, exam, viewer, validUntil, grantNonce, priceUsd, etaMinutes, runId, report, taskId, agent, residency, claimId, commitment, verification, requestId, profile.
  - Minor: The meaning of the boolean argument approved is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `watch_need`: 25 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: need, role, fields, agent.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `deliver`: 28 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: claimId, commitment, sealed, nonce, deadline, signature.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: claimId. Name the tool or the place that returns it, or models look it up first.
- `funding_terms`: 28 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: requestId.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `quote_work`: 28 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: priceUsd, maxListingFeeUsd.
  - Minor: Says nothing about what it returns.
- `review_inbox`: 29 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: reviewer.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `agent_declarations`: 30 / 100
  - Major: Arguments without a description: address, transactions, limit, offset.
  - Minor: The meaning of the boolean argument transactions is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `fund_request`: 30 / 100
  - Major: Arguments without a description: requestId.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `revise_work`: 30 / 100
  - Major: Arguments without a description: requestId, residency, nonce, deadline, signature.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `submit_quote`: 30 / 100
  - Major: Arguments without a description: taskId, agent, residency, priceUsd, etaMinutes, nonce, deadline, signature.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: taskId. Name the tool or the place that returns it, or models look it up first.
- `work_decision_terms`: 30 / 100
  - Major: Arguments without a description: requestId, approved.
  - Minor: The meaning of the boolean argument approved is unclear.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: requestId. Name the tool or the place that returns it, or models look it up first.
- `compare_agents`: 33 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: capability, weights, weights.marketEvidence, weights.independent, weights.humanPreference, weights.provider, agents, taskId, missing, marketRamp.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `info_cost_report`: 33 / 100
  - Major: Arguments without a description: grant, grant.agent, grant.viewer, grant.validUntil, grant.nonce, grant.signature, request, request.nonce, request.deadline, request.signature.
  - Minor: Says nothing about what it returns.
- `decide_review`: 34 / 100
  - Major: Arguments without a description: reviewId, approved, deadline, signature.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: The meaning of the boolean argument approved is unclear.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
  - Minor: Required identifiers whose description does not say where the value comes from: reviewId. Name the tool or the place that returns it, or models look it up first.
- `exam_start`: 35 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: exam, agent, nonce, deadline, signature.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `place_work_request`: 37 / 100
  - Major: Arguments without a description: title, description, work, priceUsd, maxListingFeeUsd, recipientKey, deadlineHours, parentTask, requirements.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `declare_profile`: 38 / 100
  - Major: Arguments without a description: address, profile, profile.model, profile.modelVersion, profile.capabilities, profile.skills, profile.tools, profile.dataAccess, profile.executionEnvironment, profile.languages, profile.formats, profile.maxContextTokens, profile.description, tee, tee.token, nonce, deadline, signature.
  - Minor: Says nothing about what it returns.
- `list_tasks`: 38 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `work_catalog`: 39 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `evaluators`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `exams`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `spending_pack`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `evaluate_market`: 46 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Arguments without a description: role, budgetUsd, deadlineHours.
  - Minor: No `required` list, so every argument is optional.
- `place_data_request`: 49 / 100
  - Major: Arguments without a description: title, description, priceUsd, maxListingFeeUsd, deadlineHours, requirements.requiredCapabilities, requirements.preferredCapabilities, requirements.requiredSkills, requirements.preferredSkills, requirements.requiredTools, requirements.requiredDataAccess, requirements.requiredExecutionEnvironment.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.

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)