Server Quality Checklist

Tool Scores

• get_activityB
  3.3/5.0
  Behavior2/5

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

  With no annotations at all (no readOnlyHint, destructiveHint), the description carries full burden of behavioral disclosure. It doesn't state whether this is a read-only operation, whether it requires specific permissions, or what happens if the activity doesn't belong to the authenticated athlete (404, access errors). No behavioral features are disclosed beyond the basic return action.

  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?

  A single concise sentence with zero waste. Every word contributes to purpose. Front-loaded with the verb 'Return' and immediately clear about scope.

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

  Completeness3/5

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

  For a single-parameter fetch tool with no output schema, the description is reasonably complete — it explains what it returns. However, with no annotations declaring this as a non-mutating read operation, and no explicit mention that the activity must belong to the authenticated athlete or what error occurs otherwise, there's a modest completeness gap. Still, given tool complexity is low, it approaches adequacy.

  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% — the single parameter activity_id already has a description ('Strava activity ID') including type constraints. The tool description adds no parameter details beyond referring to 'one of the authenticated athlete's activities,' which confirms the ID belongs to that athlete. Baseline 3 is appropriate when schema does the documentation work.

  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 returns the detailed record for one activity, with specific verb (Return) and resource (detailed record for an activity). It distinguishes from siblings: 'one of the authenticated athlete's activities' clarifies it's singular vs list_my_activities. However, it doesn't explicitly differentiate from get_my_profile, though the difference is fairly obvious.

  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 it's for fetching a single activity by ID ('one of the... activities'), which implies you need the activity_id. But there's no explicit when-to-use guidance, no alternative named, and nothing about needing to first obtain activity IDs via list_my_activities.

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

• list_my_activitiesB
  3.4/5.0
  Behavior3/5

  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 this is a listing operation scoped to the authenticated athlete and returns them in reverse chronological order, which is useful behavioral context. However, it doesn't disclose pagination behavior, number of results returned without pagination, or whether activities include full detail or are summaries.

  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?

  Single sentence, zero wasted words, front-loads the core purpose. It's appropriately concise but could arguably add a footnote about pagination without excessive bloat.

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

  Completeness3/5

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

  For a list tool with no output schema and no annotations, the description is functional but minimal. It covers the core purpose and ordering but lacks guidance on pagination defaults, result caps, or how it relates to the get_activity sibling. Parameter count (4) is moderate and all are documented, but behavioral completeness is thin.

  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 4 parameters (page, after, before, per_page). The description adds no new parameter semantics beyond what's in the schema. Baseline 3 is appropriate since schema fully handles parameter documentation.

  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 verb (List), resource (authenticated athlete's activities), and scope (reverse chronological order). It distinguishes from siblings (get_activity retrieves a single activity, get_my_profile retrieves profile) reasonably well, though it doesn't explicitly name them as alternatives.

  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 this returns a list of the authenticated user's own activities, and page/per_page params signal pagination usage. However, it doesn't explicitly state when to use this vs. get_activity (which presumably returns a single activity by ID), and gives no guidance on pagination strategy or rate limits.

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

• get_my_profileA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It's a read operation (zero parameters, 'return...profile'), and this is reasonably clear from 'Return' and zero required parameters. However, it doesn't detail aspects like whether profile includes full settings, pagination, or any edge cases in the returned data.

  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?

  One sentence, zero waste. It includes the essential verb, resource, and scope (authenticated athlete). Perfectly concise for the complexity involved.

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

  Completeness3/5

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

  The tool is simple (zero params, no output schema, no annotations), but there's still room for more context about what 'profile and settings' includes—such as whether it covers privacy settings, units, or other configuration. No output schema exists, so describing return content would add value. Still, for a zero-param read of one's own profile, it's reasonably adequate.

  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?

  This tool has 0 parameters, so the baseline for parameter semantics is 4 per the rubric. The description appropriately explains what will be returned (profile and settings), which is the complete need for parameter semantics on a zero-param call.

  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 'Return the authenticated athlete's Strava profile and settings' clearly states the verb (return) and resource (athlete profile and settings). It's specific about what data is returned, though it doesn't explicitly distinguish from siblings like get_activity. However, the resource 'profile and settings' is distinct enough from activity-level tools.

  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 this is for retrieving the authenticated user's own profile. Sibling tools like get_activity and list_my_activities are clearly activity-focused, so an agent could reasonably infer when to use this tool. However, there's no explicit when-to-use vs alternatives guidance.

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