Server Quality Checklist

Tool Scores

• explain_runA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of explaining behavior. It discloses that the tool does not re-run the job, and it specifies the return format: 'the same enriched schema analyze_job produces, with each finding carrying fix/call_site/calls/evidence.' This provides good insight into what to expect, though it stops short of discussing error handling or validation.

  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 a structured docstring with a clear summary, a clarifying paragraph, and an Args section. It is not overly long and every sentence adds value, though the separate paragraph could be slightly tightened. Overall, it is well-organized and front-loaded.

  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 tool has only one parameter, no output schema, and no annotations, the description provides sufficient context: it explains the use case, the parameter meaning, and the return format. It is complete for the tool's 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?

  The input schema provides only a type for 'path', but the description adds critical context: 'Path to a JSON file written by `wherewent run --save`.' This tells the agent exactly what kind of file is expected, greatly enhancing the semantics beyond the raw 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 returns enriched analysis from a saved wherewent JSON file, specifying the verb 'Return' and the resource. It distinguishes itself from the sibling analyze_job by explicitly targeting the 'already ran under wherewent run --save' case, making the purpose unmistakable.

  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 explicitly identifies the intended use case: 'For the "job already ran under `wherewent run --save out.json`" case — no re-run.' This clearly indicates when to use this tool, though it does not explicitly name analyze_job as the alternative for re-running, leaving that inference to the sibling context.

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

• analyze_jobA
  4.6/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and does so excellently. It discloses the trust boundary (executed with NO shell), timeout behavior with partial results and timed_out=True, and return envelope fields. This goes well beyond a generic read/write hint.

  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 text is longer than average, but every section earns its place: purpose, usage, Args, and Returns. Information is front-loaded and structured logically, making it easy to scan and apply.

  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?

  For a complex tool with no annotations and no output schema, the description is remarkably complete. It covers purpose, usage, parameters, security, timeout behavior, return format, and even how to act on findings. This is more than sufficient for correct tool selection and invocation.

  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?

  Schema description coverage is 0%, but the description compensates fully. It explains command as an argv list with security implications, unit_function as a spec for per-unit trend analysis, and timeout_s with default and partial-result behavior. Every parameter is given meaningful context beyond the raw schema.

  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 clearly states it runs a Python/SQLAlchemy job under wherewent and returns why it was slow, with specifics like call site, query count, and fix. It is a specific verb+resource+outcome, but it does not explicitly compare itself with the sibling tool explain_run, even though the use case is implied.

  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?

  "Use when a batch job is slow and you need the exact call site, query count, and fix" provides clear context for when to invoke. However, there are no explicit when-not-to-use conditions or named alternatives, so it stops short of a 5.

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