Server Quality Checklist

Tool Scores

• describe_specA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden and details the exact output contents: computed watts, duration, elapsed time, total duration, average/normalised power, IF, TSS, and total work. It implies a read-only sanity-check behavior but does not state side effects or error handling, so a notch below 5.

  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: purpose, output details, and usage guidance. It is front-loaded with the main verb and resource and contains no filler, earning a perfect score.

  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 single-parameter tool with an output schema and no annotations, the description covers what it does, what it returns, and when to use it. It does not address invalid inputs or errors, but those are lower priority given the tool's sanity-checking purpose and sibling support.

  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 sole parameter 'spec' is an opaque object with 0% schema coverage. The description adds that it is a 'workout spec' containing 'every block' and mentions watts and duration, which partially helps. However, it does not define the required structure of the spec object, so the parameter remains somewhat ambiguous.

  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 uses the verb 'Render' with the resource 'workout spec' and specifies the output as a 'human-readable block table', which clearly differentiates it from sibling render tools (render_zwo, render_garmin) and validate_spec. The purpose is immediately clear.

  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?

  It explicitly says 'Use this before rendering', giving a clear when-to-use context and contrasts with XML rendering ('it is much easier to spot a wrong number here than in XML'). It does not explicitly name alternatives or when-not-to-use cases, but the context is sufficient for a 4.

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

• spec_schemaA
  4.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool returns schema and notes, and the verb 'Return' implies a non-mutating operation, but it doesn't explicitly confirm read-only behavior, permissions, or potential side effects. For a simple schema retrieval tool, this is a minor gap, but more transparency would be beneficial.

  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 exactly two sentences, front-loading the purpose in the first sentence and adding usage guidance in the second. There is no fluff; every word contributes meaning.

  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 tool with an output schema, this description covers the essential context: what it returns and when to call it. The existence of an output schema means return values don't need to be spelled out, and the usage guidance makes the tool self-contained.

  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 tool takes zero parameters, so the description doesn't need to explain parameter semantics. It correctly references the domain ('workout spec') which adds context beyond the empty schema. Baseline 4 applies due to zero parameters.

  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 uses a specific verb ('Return') and identifies a clear resource: 'workout spec's JSON schema plus the notes needed to author one.' This clearly explains what the tool does and distinguishes it from sibling tools like validate_spec or render_zwo, which serve different purposes.

  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 second sentence provides explicit when-to-use guidance: 'Call this before writing a spec by hand if the format is not already known.' This tells the agent the appropriate context, though it doesn't explicitly name alternatives or state when not to use the tool beyond that condition.

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

• render_garminA
  4.6/5.0
  Behavior5/5

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

  With no annotations provided, the description takes on full disclosure. It reveals that the returned payload is ready for upload_workout unchanged, explains how power targets and percentages are resolved (power.between, FTP), and details the RepeatGroupDTO endCondition handling to avoid corruption. It also clarifies the tool's non-upload behavior.

  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 concise and front-loaded: the first sentence states the primary purpose, followed by two focused paragraphs covering conversion details and usage caveats. Each sentence adds functional information without redundancy.

  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?

  The description covers the core behavior, output readiness, transformation rules, non-upload caveat with an alternative, and the optional out_path. Since an output schema exists, return-value documentation is not needed. It stops short of documenting error cases or prerequisites, but the overall context is sufficient for a complex rendering 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 schema provides only parameter names and types, with no descriptions (coverage 0%). The description compensates by explaining that out_path writes JSON to disk and by describing how the spec's FTP and percentage targets are interpreted. However, the spec object's full structure is not spelled out, leaving some ambiguity.

  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 first sentence, 'Render a workout spec to a Garmin Connect workout payload,' gives a specific verb and resource. The name render_garmin distinguishes it from sibling render_zwo (Zwift rendering), and the description further clarifies it produces a payload for Garmin Connect, not an upload.

  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 includes an explicit exclusion: 'This server does not upload,' and points to the garmin-upload skill as the alternative that uploads and verifies. While it doesn't explicitly contrast with render_zwo, the distinct format and the clear purpose make selection clear.

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

• render_zwoA
  4.7/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden. It discloses the returned XML/filename, the filename-based naming quirk, explicit Ramp block emission, repeat flattening, and the optional disk write—going well beyond a basic mutation/render description.

  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 front-loaded with a one-sentence purpose, then each subsequent paragraph adds meaningful behavioral detail. No sentence is wasted; it covers output, naming, rendering quirks, and side effects without padding.

  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 an output schema and rich behavioral description, the return format, filename significance, rendering transformations, and filesystem side effect are all addressed. The sibling tool set (render_garmin, validate_spec, etc.) provides enough surrounding context for a capable agent to select and invoke this tool correctly.

  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?

  Schema description coverage is 0%, so the description must compensate. It clearly explains out_path ('pass out_path to also write the file to disk; the content is returned either way') and highlights spec.filename as the control for the upload name. The remaining spec structure is delegated to a linked spec_schema tool, but the key parameter behaviors are covered.

  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 opens with a specific verb+resource+format: 'Render a workout spec to a MyWhoosh-compatible .zwo file.' This clearly distinguishes it from the sibling render_garmin tool by target platform and output format.

  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 clear context: this is for MyWhoosh-compatible .zwo output, and it highlights important usage details like the filename controlling the library name and optional out_path for disk writes. It does not explicitly contrast with render_garmin or state when not to use it, 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.

• validate_specA
  4.7/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full burden. It thoroughly discloses behavior: what kinds of problems are detected, that unknown keys are reported as warnings, and that the tool returns valid/errors/warnings plus a summary. This goes well beyond minimal coverage.

  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 front-loaded with a one-sentence purpose, followed by a focused list of concrete error categories and a clear statement of return values. Every sentence adds value; there is no fluff or redundancy.

  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's complexity and the sparse input schema, the description is remarkably complete. It explains the return shape, enumerates specific validation checks, and notes the warning behavior for unknown keys. The presence of an output schema also helps, but the description alone provides enough context for effective use.

  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 schema only defines 'spec' as an object with additionalProperties, providing no semantic detail. The description compensates by enumerating the kinds of content in the spec (durations, power, FTP, ramps, repeats, unit forms) and explaining how certain values are interpreted. It does not provide a full structural breakdown, but the added context is substantial.

  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 opens with a specific verb+resource: 'Check a workout spec and report every problem found.' It clearly distinguishes validation from sibling tools like describe_spec or render_zwo by focusing on error detection rather than description or rendering.

  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 clearly implies when to use the tool: before relying on a spec, to catch mistakes that would cause problems downstream. It does not explicitly name alternatives or state when not to use it, but the context and error-focused language make the intended usage clear.

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

• verify_garmin_uploadA
  5/5.0
  Behavior5/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure, and it excels: it reveals that the comparison is against the sent payload ('not against an assumed read shape'), that it catches specific silent corruptions, what limitations exist (power target units, head-unit display), and that it makes no network access. This gives the agent a thorough understanding of the tool's exact behavior and edge cases.

  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 information-dense but every sentence earns its place. It is logically structured: purpose, how to invoke, key nuance, limitations, and final safety note. It is not bloated; the length is justified by the subtle failure modes it must convey. The main action is 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's complexity, the lack of annotations, and the bare schema, this description is complete. It covers what the tool does, how to use it, what it cannot verify, and what to do instead. The output schema exists but the description already provides the essential return semantics. No major gaps remain.

  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%, so the description must fully explain the parameters, and it does: 'payload' is defined as the payload given to upload_workout, and 'fetched' as the response from get_workout_by_id. It also clarifies the return value (list of differences, empty means success). This completely compensates for 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 opens with a specific verb and resource: 'Check that Garmin stored the workout that was actually sent.' It clearly distinguishes this verification tool from the sibling rendering/validation tools, and the comparison logic is explicitly described. It leaves no ambiguity about what the tool accomplishes.

  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 gives explicit operational instructions: 'Pass the payload given to upload_workout, and the response from get_workout_by_id for the workout it created.' It also states when not to rely solely on the tool by listing the two things it cannot prove and recommending manual confirmation in Garmin Connect. This is exemplary when-to-use guidance.

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