Server Quality Checklist

Tool Scores

• coverage_forA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations provided, the description carries the full burden of explaining the tool's behavior. It clearly states that the tool is a read-only query ('Ask... Returns...'), enumerates what the response includes, and adds context for interpreting results (thin vs. well-evidenced). It does not mention permissions or side effects, but for a non-mutating coverage tool, this is sufficient.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three sentences, each earning its place: the first states the purpose and timing, the second details the return values, and the third gives usage guidance. It is front-loaded with the key intent and contains no filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's simplicity (one parameter, no output schema), the description is nearly complete. It explains what the tool does, when to use it, and what it returns. It could optionally mention the response format in more detail, but the enumerated return components (claim count, operators, sweeps) make the tool comprehensible for an agent.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already provides 100% coverage for the single parameter 'subject' with a description. The tool description does not add significant extra meaning beyond referring to 'a subject' in the first sentence, so it matches the baseline of 3 for high schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description directly states the tool's function: asking how well-evidenced a subject is, and enumerates the specific outputs (number of claims, distinct operators, and sweeps). This clearly distinguishes it from siblings like search_claims (which retrieves claims) and corpus_stats (which provides overall statistics).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives explicit guidance on when to use the tool: 'Call this first on any question where being wrong is expensive.' It also instructs the agent to 'relay a thin result rather than answering around it,' telling it how to act on the output. However, it does not explicitly mention when not to use it or name alternatives, so it stops short of a full 5.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• corpus_statsA
  4.3/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations exist, so the description must convey behavior. It discloses that the tool evidences 'silence' or absence, which is a non-obvious behavioral trait. It implies read-only operation by describing corpus contents. However, it doesn't detail output format or potential side effects, though with 0 params, that's a minor gap.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences with zero wasted words. The key information is front-loaded in the first sentence, and the second provides actionable usage guidance.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite lacking an output schema, the description adequately describes the tool's role and when to use it. It's simple (0 params), so the description is nearly complete. The only missing piece is what the actual output looks like, but for a stats tool, the purpose is self-explanatory.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With zero parameters, the schema already fully covers the input contract. Per baseline for 0-param tools, this is a 4. The description adds no parameter-specific detail, but none is needed.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific phrase 'What this corpus contains and, more importantly, what it does NOT' to convey it reports corpus contents and gaps. It distinguishes from search_claims and coverage_for by focusing on corpus-level stats rather than searching or coverage checking. However, it lacks an explicit verb like 'returns' or 'calculates', slightly reducing clarity.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicitly states when to call: 'when you are about to say the corpus has no answer', framing it as a verification tool for absence claims. This provides clear contextual guidance and implies alternatives (search_claims for searching, coverage_for for coverage) without naming them.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• search_claimsA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description fully discloses behavior: every result carries a verbatim quote and a working permalink, and the tool returns an explicit no-coverage notice when the corpus lacks an answer, with instruction to relay rather than fabricate. This goes well beyond the bare minimum and helps the agent set expectations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is only three sentences, front-loaded with the core purpose and use cases. Every sentence earns its place—purpose, usage, and critical output/behavior—with no redundancy or filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Considering 8 parameters, no output schema, and no annotations, the description covers purpose, output characteristics, and the no-coverage edge case, which is substantial. It could be slightly more complete by explaining how search results relate to sibling tools or when coverage stats might be the more appropriate tool, but overall it is adequate for a complex search tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 88% (baseline 3), and the schema already provides deep semantics for 'rail' and 'buy_type'. The description adds no parameter-specific meaning beyond what the schema offers, so it does not elevate the score.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Specific verb+resource: 'Search receipt-backed claims from operators...' and enumerates concrete use cases ('how to price a creator, where to source them, how to brief them, what to test, what failed'). The tool is clearly differentiated from siblings (coverage_for, corpus_stats) by its focus on searching for evidence rather than reporting coverage or stats.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicitly states when to use the tool: 'Use it for how to price a creator, where to source them, how to brief them, what to test, what failed.' However, it does not mention alternatives or situations where a sibling tool would be preferred, so it misses explicit exclusion guidance.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.