Server Quality Checklist

Tool Scores

• garmin_list_activitiesA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, so the description adds value by detailing the output format (columns). However, no additional behavioral traits (e.g., data freshness, pagination limit) are disclosed beyond what annotations and parameter schema provide.

  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 a single focused paragraph with the main purpose first, then a compact list of columns. Every sentence is useful—no redundancy or fluff.

  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 explains the date range defaults, column output, and activity_type rollup. It lacks mention of sorting (newest first, though that's in the limit description) and total count, but given the presence of an output schema and annotations, it is mostly complete.

  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 coverage is 100%, giving a baseline of 3. The description adds significant meaning by explaining the activity_type rollup behavior (e.g., virtual_ride -> 'cycling'), which is not in the schema. This extra context justifies a 4.

  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 'List Garmin activities in a date range as a compact table', providing a specific verb and resource. It also includes column details and mentions the relationship to garmin_get_activity_detail, but does not explicitly distinguish from siblings.

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

  Usage Guidelines3/5

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

  The description implies usage by referencing activity_id 'for garmin_get_activity_detail', hinting at a workflow, but does not provide explicit when-to-use or when-not-to-use guidance compared to siblings.

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

• garmin_get_sleepA
  4.2/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, which the description implicitly supports. The description adds constraints (max 31 days, default 7 days) and a data-source transparency note about Oura ring discrepancies. 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.

  Conciseness5/5

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

  Three sentences efficiently convey purpose, output columns, range, and usage note. No extraneous content; front-loaded with key information.

  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?

  With output schema present, the description covers the essential purpose, data shape (columns), and usage constraints. The only minor gap is lack of explicit return format (how rows are organized), but it is implied by 'per night'. Complete enough for a simple read 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 coverage is 100% with clear definitions of start_date and end_date, including the night-ending interpretation. The description does not add significant meaning beyond the schema, only restating the range. Baseline score of 3 is appropriate.

  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 retrieves Garmin sleep data per night, specifies a table format with column details, and indicates a maximum 31-day range. This distinguishes it from sibling tools like garmin_get_daily_summary or garmin_get_activity_detail, which cover different data types.

  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 explains the default range (last 7 days) and maximum (31 days), and includes a note about Oura ring as an alternative source for sleep data. However, it does not explicitly state when not to use this tool or recommend specific siblings for other purposes.

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

• garmin_get_activity_detailA
  4.5/5.0
  Behavior4/5

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

  Annotations indicate readOnlyHint=true, and description consistently presents a read operation. Adds detail about what the 'detailed' mode returns (lap splits, HR-zone breakdown) beyond annotations. Could mention rate limits or auth, but overall transparent.

  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?

  Highly concise: a single sentence that front-loads the main purpose, lists key metrics, and provides actionable instruction. No filler.

  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 output schema exists, description doesn't need to detail return values. It covers all necessary context: what data is retrieved, the two modes, and prerequisite. Complete for this 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?

  Schema coverage is 100%, baseline 3. Description adds meaning by elaborating on response_format values: 'concise' vs 'detailed' with specific added data. This goes beyond the schema's simple enum description.

  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?

  Description starts with 'Deep-dive a single Garmin activity' and lists specific metrics (distance, time, HR, etc.), clearly stating the tool's purpose. It distinguishes itself from siblings by mentioning how to get the activity_id from garmin_list_activities.

  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 instructs to get activity_id from garmin_list_activities first, providing a prerequisite. Explains the two response_format options ('concise' vs 'detailed'). Does not explicitly state when not to use, but the context is clear given sibling tools.

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

• garmin_get_training_statusA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true, so no destructive behavior. Description adds value by listing all returned data fields (readiness, status, load, VO2max, HRV, predictions). Could mention that this is a snapshot at current time, but otherwise transparent.

  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: first lists data points, second gives usage guidance. Every word serves a purpose, no 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?

  With no parameters, readOnlyHint annotation, and output schema present, the description fully covers what the tool returns and when to use it. No gaps.

  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?

  No parameters defined, so description does not need to add parameter semantics. Baseline 4 for 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?

  Description explicitly states verb 'get' and resource 'training status' and lists the specific data elements (readiness score, status, acute load, VO2max, HRV, race predictions). It distinguishes from siblings by focusing on training status snapshot, unlike daily summary or activity detail.

  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?

  Clearly states when to use: 'how is my training going / how recovered am I' questions. Also suggests combining with oura_* for cross-source checks. Lacks explicit when-not-to-use or comparison with other Garmin sibling tools, but usage context is clear.

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

• garmin_get_body_compositionA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true, and the description adds that it returns a table with specific columns, max 90 days, default 30, and only days with measurements, providing full behavioral transparency beyond annotations.

  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, front-loaded with the core purpose and key constraints, no wasted words, perfectly concise.

  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 optional parameters with full schema descriptions, an output schema exists, and the description covers output shape and constraints, the definition is fully complete for agent decision-making.

  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 already describes parameters with 100% coverage (ISO dates, defaults), and the description adds context about the maximum range and default behavior, meaningfully extending 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 returns body composition entries as a table with specific columns and a date range limit, distinguishing it from sibling tools like garmin_get_daily_summary or garmin_get_sleep.

  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 implies usage for retrieving body composition data within a date range, but does not explicitly state when not to use or compare to alternatives; however, sibling tools are distinct enough that the purpose is clear.

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

• garmin_get_daily_summaryA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true, and the description adds valuable behavioral details: max 31-day range, default last 7 days, and the format of the output as a compact table. 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.

  Conciseness5/5

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

  The description is two well-structured sentences followed by a clear list of columns and sibling references. Every sentence provides necessary information without 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 has an output schema and the description lists all columns, the behavioral context is fully covered. Sibling tool references and parameter constraints provide complete context for an AI agent.

  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 coverage is 100% with detailed descriptions for both parameters. The description adds contextual value by stating the maximum range (31 days) and default range (last 7 days), which goes beyond the schema's syntax.

  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 that the tool provides daily Garmin health metrics in a compact table format and lists all columns explicitly. It distinguishes itself from sibling tools by referencing garmin_get_sleep and garmin_list_activities for specific use cases.

  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 tells when to use alternatives: for sleep detail use garmin_get_sleep and for workouts use garmin_list_activities. It also implies this tool is for general daily health metrics, providing clear context for selection.

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