Server Quality Checklist

Tool Scores

• search_grounded_evidenceA
  4.5/5.0
  Behavior5/5

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

  With no annotations provided, the description fully bears the transparency burden. It discloses async behavior, approximate runtime (60-120s), non-blocking nature, and exactly what the final result contains (novelty verdict, evidence items, citations, contradiction, etc.). It also explains error handling for invalid input. This is exceptionally transparent.

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

  Conciseness4/5

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

  The description is well-structured with clear sections: first line states purpose, then async behavior, then parameter details, then return format. While it is slightly verbose, every sentence adds value. It is front-loaded with the main purpose, aiding quick comprehension.

  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 complexity (async, long-running, sibling tool comparison), the description covers most key aspects: purpose, usage, parameter constraints, return format (including error handling and disclaimer). It does not mention rate limits or authentication, but those are not critical for understanding how to use the tool.

  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?

  The input schema has 0% description coverage, so the description must add meaning for the single parameter `question`. It adds character length (3-8000), domain scope (clinical/pharmacological/mechanistic), and type (free-text). This provides useful constraints beyond the schema's bare type definition.

  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 clearly states the tool's verb ("Look up"), resource ("PubMed-grounded mechanistic evidence"), and scope (any clinical/pharmacological/mechanistic question). It distinguishes itself from sibling `generate_experiment` by being lighter-weight and a fallback tool, and even notes it is not limited to any one domain, providing strong purpose clarity.

  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 provides explicit guidance on when to use (any question) and how to use (async submit+ poll, must poll `get_experiment_result`). It also compares to `generate_experiment`. However, it does not explicitly state when not to use this tool, such as when full experiment details are needed, though this is implied by the omission list.

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

• generate_experimentA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses the async behavior, pipeline steps, expected runtime, immediate return of a job handle, and the need to poll. It also describes error cases, input validation, and dependencies like ANTHROPIC_API_KEY, and includes a research-only disclaimer.

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

  Conciseness4/5

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

  The description is well-structured and front-loaded with purpose and async behavior. It is fairly long but each section (overview, async explanation, args, returns) earns its place. Minor redundancy could be trimmed, but overall it is appropriately concise for the complexity.

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

  Completeness5/5

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

  Given the complexity of an async multi-step pipeline, the description is highly complete. It explains the pipeline steps, the final TransBrief content, error handling, and return shapes for both statuses. The output schema is mentioned, and the description covers everything needed for correct usage.

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

  Parameters5/5

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

  Despite 0% schema description coverage, the description provides detailed parameter documentation in an Args section: observation with length constraints and examples, focus_drug with default and optional usage. This adds significant meaning beyond the bare schema.

  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 clearly states the tool generates a 'grounded translational research brief' from any clinical/biomedical observation, with specific examples. It differentiates itself from siblings by explaining its async nature and that it initiates a pipeline, while 'get_experiment_result' is for polling and 'search_grounded_evidence' is for searching.

  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 provides explicit when-to-use guidance: for any clinical/biomedical observation. It explains the async workflow and the need to poll for results. It gives example inputs but does not explicitly state when not to use it, though the context makes it clear.

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

• get_experiment_resultA
  4.7/5.0
  Behavior5/5

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

  No annotations provided, but description fully discloses async polling behavior, all possible response formats (running, done, error, unknown_job), and TTL (~30 min). No contradictions.

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

  Conciseness4/5

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

  Well-structured with Args/Returns sections, front-loaded purpose. Slightly verbose but necessary for complex async polling behavior.

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

  Completeness5/5

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

  Covers all aspects: polling, statuses, error handling, TTL. Output schema effectively described in return section. No gaps given complexity.

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

  Parameters5/5

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

  Single parameter job_id with no schema description. Description explains its origin (from sibling tools) and usage, fully compensating for 0% 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?

  Clearly states it polls for results of async runs from generate_experiment or search_grounded_evidence. Uses specific verb 'Poll' and resource 'experiment result', distinct from siblings that initiate the async tasks.

  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 tells when to use (after async call), provides polling interval (~5s), explains return states and when to stop. Does not explicitly state when not to use, but context is clear enough.

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