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

Annotations provide readOnlyHint; description adds pagination and filtering context, 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.

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

Two sentences, no fluff, front-loaded with purpose and key capabilities.

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

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

Adequately covers pagination, date filtering, type filtering, and points to detail tool; lacks output format info but acceptable for browsing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaning beyond schema by explaining Unix-second date bounds and client-side activity type filtering, covering 60% schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it browses activity summaries in manageable pages, distinguishes from getActivity for full details.

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

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

Explicitly recommends getActivity for detailed data, but doesn't address when to use siblings like getRecentActivities.

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

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

Annotations declare readOnlyHint=true, and the description adds value by explaining pagination (nextPage, scanning up to limit), ordering (newest first), and date range constraints (after/before as Unix seconds). It does not contradict annotations. Minor omission: no mention of rate limits or authentication, but acceptable for a read-only paginated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is only two sentences, front-loaded with the core purpose, and immediately provides key details. Every word earns its place; no redundancy or filler.

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

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

For a tool with 5 parameters and no output schema, the description covers the essential aspects: type filter, pagination flow, and optional date range. Sibling tools exist but the description is self-contained. It could mention that the output includes activity summaries, but given the tool's simplicity, it is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80% (4 of 5 parameters have descriptions). The description adds meaning beyond the schema: clarifies that 'limit' is a scan limit, explains pagination with 'nextPage', and reiterates the date range parameters' unit (Unix seconds). The 'page' parameter is described as 1-based. This adds useful context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a bounded page of activities of a supported type, newest first. It specifies the verb ('returns'), resource ('activities'), and key constraints (type filter, pagination, ordering). This distinguishes it from sibling tools like getActivities (likely all types) and getRecentRuns (specific type implied).

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

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

The description explains when to use the tool: to retrieve activities of a specific type with pagination and optional date range. However, it does not explicitly state when not to use it or mention alternatives among sibling tools. The context is clear but lacks exclusion guidance.

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

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

Annotations declare readOnlyHint=true, which the description does not contradict. Description adds behavioral detail that metric splits and embedded laps are returned 'when Strava provides them', indicating optional content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence, front-loaded with usage context, no wasted words. Achieves maximum conciseness.

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

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

For a simple 1-parameter, read-only tool, the description covers main purpose and return content hints. Could mention error handling, but is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description only indirectly mentions the parameter ('after finding an activity ID'). It does not add explicit details about the activityId parameter beyond the schema constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns full activity detail including metric splits and embedded laps. The verb 'Returns' and resource 'activity' match the tool name, and it distinguishes from sibling tools like getActivityLaps.

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

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

The phrase 'Use after finding an activity ID' provides clear prerequisite context. It implies this is the primary detail endpoint, but does not explicitly state when not to use it vs. siblings like getActivityStreams.

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

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

Annotations indicate readOnlyHint=true; description adds data types returned but does not cover edge cases (e.g., no laps) or error behavior. Adequate but not enhanced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single, front-loaded sentence with zero wasted words. Highly concise and to the point.

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

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

For a simple read-only tool with no output schema, the description adequately covers the returned data types and usage context, though could mention empty/error cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage 0%; description does not explain the activityId parameter or its format, relying solely on the schema constraint. Adds minimal value beyond the structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool retrieves lap-by-lap analysis for pacing, HR, cadence, and elevation, distinct from sibling tools like getActivityStreams or getActivity.

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

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

Explicitly states the condition 'when an activity has recorded laps', providing clear use context, though no direct alternatives or negations are mentioned.

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

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

Adds behavioral context beyond annotations: 'Strava returns only available streams' and describes default selection behavior when streamTypes is omitted. Annotations already indicate readOnlyHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, front-loaded with purpose, no wasted words. Efficient and clear.

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

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

Given 2 parameters, no output schema, and annotations present, the description fully explains purpose, parameter usage, and behavioral notes. Complete for agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 50% schema coverage, description adds meaning: explains default behavior for omitted streamTypes and advises on controlling response size. ActivityId is implicitly understood.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Use for point-by-point analysis' and implies retrieval of activity streams. Distinguishes from siblings like getActivity which likely returns summary data.

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

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

Advises to request only needed stream types to control response size and notes that omitting streamTypes selects a useful default set. Provides clear guidance on parameter usage.

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

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

Adds beyond readOnlyHint: clarifies zones only when Strava exposes them. Does not detail error conditions or empty returns, but adequate for a read-only tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two efficient sentences, front-loaded, no redundant information.

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

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

Adequate for a simple tool with one parameter and no output schema, but could benefit from a note on return structure or availability conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, description adds no meaning to the activityId parameter. Should specify that it refers to a Strava activity ID.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it returns heart-rate or power zones for time-in-zone analysis, distinguishing it from other activity tools. Could be more explicit about sibling differentiation.

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

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

Provides the context 'time-in-zone analysis' but lacks guidance on when not to use it or alternatives like getActivityStreams.

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

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

The description adds that the data is optional and separate from Strava, providing useful context beyond the readOnlyHint annotation. It does not contradict any annotations and discloses that the data may not always be present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is concise with two sentences, front-loading the purpose and adding necessary context. Every sentence provides value.

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

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

For a tool with no parameters and no output schema, the description adequately explains the data returned. However, it does not specify the structure or format of the results, which could be helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so baseline is 4. The description does not need to add parameter details, and schema coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves user-configured goals, heart-rate zones, race targets, constraints, and training preferences, distinct from Strava data. This differentiates it from siblings like getAthleteOverview or getAthleteProfile, which likely return Strava-derived data.

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

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

The description explains the tool is for use alongside Strava data and that the data is optional and separate, implying it should be called when needing personal context. However, it does not explicitly list alternatives or when not to use it.

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

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

Annotations already declare readOnlyHint=true; the description adds that it returns a compact overview and recent trends, but does not detail other behavioral aspects like data recency or computation cost.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, no filler, front-loaded with the main purpose and essential usage guidance.

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

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

For a simple read tool with no required parameters and no output schema, the description adequately covers the tool's purpose and parameter usage, though the exact contents of the overview are unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description adds meaningful context by explaining the relationship between `sinceDays` and `after` and the default window, going beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Returns a compact training overview and recent trends over a bounded look-back window' with specific verb and resource, and distinguishes from sibling tools like getTrainingHistory and getRecentActivities.

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

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

Provides guidance on using parameters to adjust the time window but does not explicitly state when to use this tool versus alternatives, nor when not to use it.

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

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

Annotations already indicate readOnlyHint=true. The description adds that it returns the authenticated athlete profile, which is useful context but not extensive behavioral detail beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two concise sentences that front-load purpose and immediately provide usage guidance. No wasted words.

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

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

The description covers purpose and usage boundaries. It is adequate for a zero-parameter read tool, though it could explicitly distinguish from similar sibling tools like getAthleteContext.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so baseline is 4. The description does not need to add parameter info.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns the authenticated Strava athlete profile for identity and baseline metadata, and explicitly distinguishes from activity tools.

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

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

It tells when to use (identity/baseline metadata) and when not to (use activity tools for training data). However, it does not differentiate from siblings like getAthleteContext or getAthleteOverview.

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

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

Annotations include readOnlyHint=true, and the description adds behavioral details: return is compact/information-dense, date derivation logic, and inclusion of inactive weeks for real gap streaks. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is concise at two sentences and adequately explains functionality. However, it could be slightly more structured, e.g., separating purpose from date logic.

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

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

Given the tool has no parameters and a readOnlyHint, the description covers all necessary context: what it returns, date derivation, and week behavior. No output schema exists, but the description sufficiently explains the return value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the description is not required to add parameter semantics. The baseline for 0 parameters is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns 'compact, information-dense run/walk training context for the current training cycle', which is a specific verb+resource. It distinguishes from sibling tools like getActivities or getAthleteContext by focusing on half marathon training context.

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

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

The description implies usage context (for current training cycle) and explains date logic, but does not explicitly state when to use or when not to use compared to alternatives. No exclusions or alternative references are provided.

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

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

The readOnlyHint annotation already signals no mutations. The description adds no further behavioral details (e.g., ordering, pagination). Beyond annotations, transparency is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single concise sentence with no redundancy. However, it could be slightly more informative without losing brevity.

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

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

For a simple read-only list tool, the description is adequate but incomplete. It does not explain the output format or the effect of the limit parameter. Given no output schema, more context would be helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage for the 'limit' parameter, and the tool description does not explain what the parameter does or how to use it. This leaves agents guessing about its purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'returns' and the resource 'most recent activities'. However, it does not differentiate from siblings like getRecentRuns or getActivities which also return activity lists.

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

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

No guidance is provided on when to use this tool versus alternatives such as getActivities or getRecentRuns. The description lacks both when-to-use and when-not-to-use instructions.

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

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

The description discloses the tool is read-only (consistent with readOnlyHint=true) and returns newest runs. It adds that results are limited by the limit parameter. No contradictions. Could mention any additional behavioral traits like sorting or absence of filters, but for a simple read tool it's adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description consists of two concise sentences. The first sentence provides usage guidance, the second states the behavior. No unnecessary text; every sentence adds value.

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

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

Given the tool's simplicity (1 parameter, no output schema, readOnlyHint annotation), the description is fairly complete. It explains the resource, ordering, and limit. It does not describe the return format or whether it returns full activity details, but this is acceptable for a list endpoint with low complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions 'up to the requested limit,' clarifying that the limit parameter controls the maximum number of results. The schema has 0% description coverage, so the description partially compensates by giving meaning to the parameter, but it does not elaborate on the default (20) or min/max constraints (already in schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the newest Run activities up to a limit, specifying verb (returns), resource (Run activities), and scope (newest, limit). It distinguishes from siblings like getRecentActivities (likely all types) and getActivitiesByType (with type filter).

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

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

The description explicitly says 'Use for current training analysis without fetching unrelated sports,' providing clear context for when to use and what to avoid. It does not name specific alternatives but implies them through the exclusion of unrelated sports.

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

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

Annotations already signal readOnlyHint=true for safety. The description adds behavioral details: pagination with bounded pages, newest-first ordering, and timestamp constraints. No contradiction; context 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.

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

Two efficient sentences: first states core purpose, second explains pagination and time range. Front-loaded, no extraneous words.

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

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

Description covers pagination and time bounds but omits return format (e.g., full activity objects). No output schema. Still, it is complete enough for a read-only paginated tool with clear usage instructions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all 4 parameters. The description mentions 'nextPage' (not a parameter) and reinforces the use of after/before as Unix seconds, but adds little new semantic meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states verb 'Returns', resource 'activities', scope 'one bounded page', sorting 'newest first', and purpose 'long-term training analysis'. This distinguishes it from siblings like getRecentActivities or getActivities.

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

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

The description explains pagination logic ('When nextPage is non-null, call again') and temporal constraints ('Use after/before'). It positions the tool for 'long-term training analysis', but does not explicitly exclude alternatives or state when not to use it.

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