Server Quality Checklist

Tool Scores

• health_queryA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It adds the critical read-only guarantee and hints at needing the schema, but it omits details like error handling, result formatting, or any potential side effects. This is adequate but not rich.

  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 concise sentences with the core purpose front-loaded in the first sentence and a useful prerequisite in the second. Every word earns its place, 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?

  For a tool with two parameters and no output schema, the description is adequately complete. It tells the user the essential prerequisite (call health_schema first) and the read-only nature. It could be more explicit about when to use this instead of health_report, but that is a minor gap given the clarity of the query intent.

  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 input schema already documents both parameters (query as a single SELECT/WITH statement, limit with max rows) with 100% coverage. The description adds no additional parameter-specific semantics, so it neither compensates for nor improves upon the 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 the tool runs a read-only DuckDB SQL query against health tables, identifying the verb, resource, and scope. It is distinguishable from siblings by emphasizing arbitrary SQL queries, though it does not explicitly name alternatives or contrast with health_report or health_schema.

  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?

  Provides clear context: use for read-only SQL queries on health data, and explicitly instructs to call health_schema first as a prerequisite. It does not specify when not to use or mention alternative tools, but the guidance is actionable and sufficient for most cases.

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

• health_reportA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses a key behavioral trait: the reply states which window was used and why, prompting verification against the requested range. It also clarifies window semantics (inclusive endpoints, relative length), though detailed parameter logic is covered in the schema. It does not mention permissions, rate limits, or error handling, but for a read-only summary tool this is reasonable.

  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 compact (two sentences) and front-loaded with the core purpose. Every sentence earns its place: the first identifies the tool's function and scope, the second explains window behavior and directs to the alternative tool. No fluff or repetition of schema details.

  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 moderate complexity (3 optional attributes, full schema documentation, no output schema), the description is complete enough. It states what the tool does, how the window works, what to verify in the response, and when to use a sibling tool. It conveys essential information for correct selection and invocation without needing to list return fields explicitly.

  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 100%, so the schema already documents all parameters thoroughly. The description adds only minimal extra meaning by framing the window as 'named relative period or explicit dates' and noting that the reply includes the window actually used. This is useful context but does not significantly enhance the parameter semantics beyond the 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 summary across multiple health metric domains (heart rate, sleep, activity, blood oxygen, workouts, CPAP therapy), identifying a specific verb and resource. It distinguishes itself from sibling health_query by scope, noting it handles broad summaries while health_query is for anything more specific.

  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?

  The description explicitly names health_query as the alternative for more specific needs, providing a clear when-to-use boundary. It also explains the window selection logic (named relative period or explicit dates) and instructs the agent to verify period.start and period.end in the reply, giving actionable guidance.

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

• health_schemaA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses the tool's informational nature and enumerates what it returns (tables, semantic layer, metrics, aggregations, traps). It could be more transparent about potential access limitations or output size, but the core behavior is clearly conveyed.

  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 the main action front-loaded in the first sentence and a clear directive in the second. No redundant words or filler; every clause earns its place.

  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 zero-parameter metadata listing tool, the description fully covers what it does, what it returns, and when to use it. The lack of output schema is not an issue because the description itself enumerates the semantic content, and the sibling tools are clearly distinct.

  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?

  There are zero parameters, and the schema description coverage is 100% (trivially). The description adds contextual meaning about the tool's purpose and return value, satisfying the baseline for parameter-less tools.

  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 identifies the tool as listing every health table and returning a curated semantic layer, including metric definitions, valid aggregate functions, and known data traps. This specific verb-resource pairing distinguishes it from the sibling tools health_report and health_query.

  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?

  The explicit instruction 'Call this before writing any query' provides clear when-to-use guidance, implying it is a prerequisite for data querying and reporting. This effectively differentiates it from health_query and health_report, which are for actual data retrieval.

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