Server Quality Checklist

Tool Scores

• get_stress_levelsC
  2.6/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does not mention the role of the 'days' parameter, any default time range, whether the data is read-only, or what 'trends' entails. The description is essentially a purpose statement and lacks behavioral depth.

  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?

  The description is a single concise sentence with no filler, and the core action is front-loaded. It is appropriately brief for a simple read tool, though it sacrifices useful detail for brevity.

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

  Completeness2/5

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

  The tool has no annotations, no output schema, and one undocumented optional parameter. The description does not explain how 'days' influences the result, what the response looks like, or any sensible defaults. An agent cannot reliably invoke this tool correctly without additional information.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description does not mention the 'days' parameter at all. The only parameter is left completely undocumented, so an agent has no basis to infer its meaning, constraints, or default behavior from the description.

  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 states a specific verb ('Returns'), a clear resource ('daily stress averages and trends'), and the data source ('Garmin Connect'). It is unambiguous about what the tool does, though it does not explicitly differentiate itself from sibling tools like get_heart_rate_trends or get_week_review.

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

  Usage Guidelines2/5

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

  No guidance is given on when to use this tool versus alternatives or what context it is appropriate for. The description only states what it returns; there are no conditions, exclusions, or references to sibling tools that might be more suitable for related queries.

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

• get_body_compositionC
  2.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'returns' trends, implying a read operation, but it doesn't disclose how trends are computed, whether data is aggregated or raw, how the time period is bounded, or what happens when no data is available. This is minimal and insufficient without annotation support.

  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?

  The description is a single, focused sentence with no wasted words. The core capability is front-loaded and easy to parse. However, it omits details about the time period parameter, which affects completeness more than conciseness; as a concise statement it works well.

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

  Completeness2/5

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

  For a tool with one parameter and no annotations or output schema, the description is incomplete for correct invocation. The agent does not know what 'days' means, how to specify the time period, or what the returned trends look like. Sibling tools don't provide this context. The description leaves critical gaps.

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

  Parameters2/5

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

  The only parameter 'days' has no schema description (0% coverage), and the description never mentions it. While the name 'days' hints at a time period, the description's 'over a time period' is not explicitly linked to the parameter. The agent cannot determine the parameter's meaning, default, or units from the description.

  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 states a specific verb ('Returns') and a distinct resource ('weight, body fat, and muscle mass trends over a time period'). This clearly identifies the tool's purpose and differentiates it from sibling trend tools like get_heart_rate_trends or get_vo2_max_trends by the metrics involved, though it doesn't explicitly name alternatives.

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

  Usage Guidelines2/5

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

  There is no guidance on when to use this tool versus the many sibling tools. It doesn't mention that it should be used for body composition metrics specifically, or provide any exclusions or conditions. The agent must rely on the tool name and description to infer its use case.

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

• get_training_insightsC
  2.9/5.0
  Behavior3/5

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

  With no annotations, the description must carry behavioral context on its own. It does indicate a read-only retrieval ('Returns') and lists the data domains, which is helpful. However, it does not explain how the 'weekly' window is determined, how the optional 'days' parameter affects results, or any aggregation behavior, leaving the agent with incomplete behavioral expectations.

  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?

  The description is a single, front-loaded sentence that immediately conveys the outcome and organizes the included metrics in a scannable list. There is no fluff or repetition, though it could have briefly addressed the 'days' parameter without sacrificing conciseness.

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

  Completeness2/5

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

  Despite having only one optional parameter, the tool lacks an output schema and annotations, and it sits among many overlapping sibling tools (get_week_review, get_sleep_data, get_recovery_status, get_stress_levels). The description fails to explain how 'days' shapes the request or how this summary differs from get_week_review, leaving significant gaps for correct invocation and routing.

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

  Parameters1/5

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

  The only parameter, 'days', is completely undocumented in both the schema and the description (0% schema description coverage). The description never mentions 'days' or explains its relationship to the weekly summary, such as whether it overrides the default week or controls look-back. The agent must guess from the parameter name alone, so the description adds zero semantic value.

  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 returns a combined weekly training summary and enumerates the included components (latest activity, recent workouts, sleep, recovery, stress). This gives a specific, understandable purpose, but it does not explicitly distinguish it from the similarly named sibling get_week_review.

  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 tool is for a high-level weekly overview by combining multiple metrics, but it provides no explicit when-to-use or when-not-to-use guidance. It does not mention that individual getters like get_sleep_data or get_recovery_status are better for focused queries, nor does it route to get_week_review for a possibly different weekly review.

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

• get_sleep_dataB
  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 behavioral disclosure burden. It does convey that the tool returns data for 'recent nights' and implies a read-only operation, but it fails to explain default behavior, how far back 'recent' reaches, or whether the 'nights' parameter controls the time window.

  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?

  The description is a single, front-loaded sentence that lists concrete output components, which is efficient and easy to parse. However, the brevity comes at the cost of missing crucial parameter and usage details.

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

  Completeness2/5

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

  The tool has one optional parameter, no output schema, and no annotations, so the description must supply essential context. It lists return fields but leaves the meaning of 'nights' and the default behavior unspecified, making correct invocation uncertain when a specific night count is requested.

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

  Parameters1/5

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

  Schema description coverage is 0% and the description does not explain the meaning or effect of the 'nights' parameter. The phrase 'recent nights' hints at a time window but never links it to the parameter, leaving the agent unable to determine how to request a specific number of nights.

  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 'Returns' and a precise resource: sleep duration, quality score, stage breakdown, and interruptions. It clearly distinguishes this tool from sibling tools focused on heart rate, stress, recovery, and other non-sleep metrics.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to choose this tool over siblings like get_recovery_status or get_week_review, nor does it mention any exclusions or prerequisites. Usage must be inferred entirely from the tool name and output list.

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

• get_heart_rate_trendsB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Returns' trends, which hints at a read operation, but it does not describe what 'over a time period' means, whether the days parameter is required, what default behavior occurs, or any units or granularity.

  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?

  The description is a single focused sentence with no wasted words. It is front-loaded with the core output type, though it sacrifices useful detail for brevity.

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

  Completeness2/5

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

  With no output schema and no annotations, the description is the only source of context, and it leaves key decisions unclear. An agent cannot confidently determine how to set the days parameter, what the returned trend data looks like, or whether calling without parameters is valid.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description does not explicitly connect the 'days' parameter to the time period or explain its semantics. The phrase 'over a time period' is vague and does not clarify whether days is optional, what the range is, or what happens when it is omitted.

  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 ('Returns') and a specific resource ('resting, max, and average heart rate trends'), making the tool's function immediately clear. It is distinguishable from sibling tools like get_vo2_max_trends or get_sleep_data because it names heart rate metrics explicitly.

  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 tool should be used when heart rate trend data is needed, but it gives no explicit guidance on when to choose it over sibling tools like get_vo2_max_trends or get_recovery_status. There are no exclusions or alternative-routing hints.

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

• get_recovery_statusB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full behavioral disclosure burden. It states what metrics are combined but does not disclose default weighting behavior, whether the weights are optional, whether the operation is read-only, or what the training recommendation contains.

  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 sentence that front-loads the core computation and output. Every phrase contributes meaning, and there is no filler or redundancy.

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

  Completeness2/5

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

  There is no output schema and no annotations, so the description must stand alone. It omits important invocation details such as what happens when no weights are supplied, how the recovery score is scaled, and what the training recommendation looks like.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the parameter names already reveal the four metrics. The description adds only that these are combined, without explaining weight semantics, valid ranges, defaults, or whether calling with no parameters is meaningful.

  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 ('Combines') and clearly identifies the resource: HRV, sleep, stress, and resting heart rate produce a recovery score and training recommendation. This distinguishes it from sibling tools like get_sleep_data or get_stress_levels, which return individual data streams.

  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 use when an aggregate recovery assessment is needed, but it does not explicitly state when to prefer this tool over overlapping siblings like get_training_insights or get_week_review. No alternatives or exclusions are mentioned.

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

• get_activities_rangeA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden; 'Returns' indicates a read operation, and the date-range constraint is stated. However, it does not disclose ordering, inclusivity of endpoints, timezone handling, pagination, or response format, leaving some ambiguity.

  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 sentence with the verb and resource front-loaded and no filler. It is appropriately sized for a two-parameter read tool.

  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 definition is complete enough for a simple date-range query, especially with schema-covered parameters. Yet the lack of output schema and absence of any note about ordering, pagination, or range limits leaves the return contract underspecified.

  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 describes both parameters as ISO 8601 strings with 100% coverage, so the baseline applies. The description reinforces the date-range concept but adds no parameter-level detail beyond 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 states a clear verb ('Returns'), a specific resource ('Garmin activities'), and a scope ('within an ISO 8601 date range'). It is distinct from siblings like get_latest_activity or get_week_review, though it does not explicitly name 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 when to use the tool: when activities in a date range are needed. It offers no explicit when-not-to-use guidance or comparison to sibling tools, so the usage context is present but not fully developed.

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

• get_vo2_max_trendsA
  3.6/5.0
  Behavior3/5

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

  'Returns' indicates a non-mutating read operation, which is the main behavioral trait. With no annotations, the description could add caveats about data freshness, availability, or authorization, but for a simple read tool this is a minimal but acceptable disclosure.

  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 front-loaded sentence with no filler. Every word adds useful information: the action, the metric, the time dimension, and the data source.

  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 high-level return value is stated, but without an output schema or annotations the description does not specify result granularity or default behavior for omitted `days`. It is minimally viable yet leaves a clear gap in how an agent should interpret or parameterize the call.

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

  Parameters2/5

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

  The schema documents only the type and bounds of `days`, and the description does not explain what `days` controls (such as lookback window or aggregation period), nor what omitting it returns. With 0% schema-description coverage, the description fails to compensate.

  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 ('Returns'), a precise resource ('VO2 max fitness trends over time'), and a source ('Garmin Connect'). This clearly distinguishes the tool from sibling metrics such as get_heart_rate_trends and get_body_composition.

  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 the use case: call when VO2 max trend data is needed. However, it offers no explicit comparison to sibling tools, no conditions, and no when-not-to-use guidance, leaving alternative selection to the agent's inference.

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

• get_latest_activityA
  3.7/5.0
  Behavior3/5

  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 returned stats, but does not mention edge cases (e.g., no activities found), time zone handling, or that this is a read-only operation. For a simple getter 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?

  The description is a single sentence that front-loads the action and resource, then lists the specific stats. Every word earns its place; no filler or redundant restatement.

  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 zero-parameter read tool, the description covers the core function well. However, it lacks differentiation from siblings and does not explain how 'most recent' is determined or what the output format is. Output schema is absent, so more return detail would help.

  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 has zero parameters, so the description need not explain parameter semantics. The baseline of 4 applies because there are no parameter details to add.

  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 states a specific verb ('Returns'), a specific resource ('most recent Garmin activity'), and the key stats (distance, duration, pace, heart rate). This clearly distinguishes it from siblings like get_activities_range by scoping to a single, latest activity.

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

  Usage Guidelines2/5

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

  No guidance is given on when to use this tool versus alternatives such as get_activities_range or get_week_review. The 'most recent' wording implies a use case, but there is no explicit context or exclusion, which is a notable gap given the large sibling set.

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

• get_user_contextA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the behavioral disclosure burden. It clearly indicates this is a read-only retrieval operation via 'Returns,' which is basic transparency. Yet it does not explain the effect of optional parameters such as on_date or the default exclusion of include_closed, nor mention any edge behavior, leaving some ambiguity about what 'on record' means over time.

  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 consists of two tightly written sentences: the first states the return value and the second gives a practical usage directive. There is no filler or redundancy, and the most important information is front-loaded.

  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 fairly simple read-only tool with fully documented optional parameters, the description covers the core return content and the primary use case in enough depth that an agent can decide to call it. It stops just short of being complete because it does not clarify how date-scoped queries behave or distinguish its output from sibling tools like get_week_review, but the absence of nested objects and output schema keeps the need low.

  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 with 100% coverage, so a baseline score of 3 applies. The description adds no additional context about how on_date or include_closed influence the returned records; the agent must rely solely on the schema's short property descriptions.

  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 ('Returns') and a concrete resource list ('goals, races, injuries and notes on record for the user'), which tells an agent exactly what data is exposed. The additional directive 'Read this before giving training advice' clarifies the tool's intended role in the coaching workflow and sets it apart from the sibling data-retrieval tools by naming its unique content categories.

  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, 'Read this before giving training advice,' provides an explicit, actionable trigger for when this tool should be called, which is strong guidance. However, it does not contrast this tool with alternatives such as get_findings or get_training_insights, nor state conditions when this tool should not be used.

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

• remember_contextA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full behavioral burden. It does convey the core write side effect and the non-Garmin scope, but it does not mention overwriting behavior, retention, how effective dates interact with the stored memory, or what happens after recording. This is adequate but only partially 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 with no filler. The purpose is front-loaded and the trigger is stated in the second sentence. Every sentence contributes useful information without repeating schema details.

  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 low-complexity four-parameter write tool, the schema already documents the parameters and the description covers why and when to use it. The main gap is that the optional effective_from/effective_to fields are never connected to the 'race and its date' example, and there is no mention of the expected confirmation or return behavior, but this is not blocking.

  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 baseline is 3. The description's enumerated examples mirror the kind enum and add no real meaning beyond what the schema already provides, and it says nothing about the optional effective_from and effective_to fields beyond what the schema states.

  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 ('Records') with a clearly scoped resource ('something about the user that Garmin does not know') and enumerates the exact kinds of things it stores. This distinguishes it from the read-only getter siblings and clarifies that it is a write/memory operation.

  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 gives an explicit trigger: use it whenever the user mentions one of these things in passing. However, it does not name alternatives or state when not to use it, so an agent is not fully guided on routing between this, log_subjective, and get_user_context.

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

• log_subjectiveA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full behavioral burden. It communicates the core behavior—recording a rated subjective feeling—and clarifies the scale and categories, but it does not disclose whether entries overwrite or append, whether authorization is needed, or what response is returned. For a simple logging tool, this is adequate but not richly 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?

  The description is two sentences with no filler. It front-loads the action and scope, lists the distinct rating types, and the 'Garmin has no equivalent' note is a useful differentiator rather than unnecessary detail.

  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 tool is simple: four parameters, two required, an enum, and no output schema. The description covers what is being logged, which values are valid, and why this tool exists separately from Garmin-derived siblings. It stops short of describing expected return/confirmation behavior or date defaulting, but these are minor for a basic logging call.

  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 100%, so the baseline is 3, but the description adds value by mapping 'rpe' to perceived effort, explaining that values range 1-10, and tying the rating to a day or session. This gives the enumerated 'kind' and numeric 'value' parameters practical meaning 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 uses a specific verb ('Records') and resource ('how a day or session actually felt'), and enumerates the exact rating kinds and scale. This clearly distinguishes it from the sibling get_* tools, which all retrieve Garmin data.

  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 subjective self-reported ratings, not objective Garmin measurements, and explicitly notes Garmin has no equivalent. It does not spell out 'when not to use' or name alternative logging tools, but among the provided siblings there is no direct alternative, so the context is sufficient.

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

• get_findingsA
  4.4/5.0
  Behavior4/5

  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 clearly conveys that the tool performs baseline comparison over a 28-day window and returns highlighted anomalies rather than raw numbers. It does not mention output format or side effects, but 'Returns' strongly implies a read-only operation and the behavioral details given are valuable.

  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 deliver both the tool's core behavior and usage guidance with no filler. The key output categories are front-loaded, and the preference statement earns its place by helping the agent decide when to invoke this tool.

  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 zero-input analysis tool, the description covers what it returns, the comparison basis, and the preferred usage scenario. It lacks an explicit output schema or example, but the enumerated finding types give sufficient context for an agent to understand the tool's role among many siblings.

  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 has zero parameters and schema coverage is 100%, so there is nothing for the description to add about parameter meaning. Per the baseline for zero-parameter tools, a 4 is appropriate; the description does not need to compensate for any schema gaps.

  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 states a specific verb ('Returns what stands out') and a clear resource ('user's stored history against their own 28-day baselines'). It enumerates concrete signals—resting heart rate elevation, sleep debt, HRV trend breaks, training load ratio—which separates it from sibling tools that return raw metrics. The preference statement further distinguishes it from raw metric retrieval tools.

  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 explicitly says to prefer this tool over reading raw metrics when asked how things are going. This gives a clear contextual trigger and an implicit alternative. It does not name specific sibling tools or list exclusion cases, but the guidance is actionable enough.

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

• get_week_reviewA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. 'Returns' clearly indicates a read operation, and the description transparently explains the projection condition ('if next week repeats this one') and that outputs are compared against the user's own baseline. It does not explicitly state side effects, but none are expected for a no-parameter read-only review.

  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?

  The description is front-loaded with the return value and contains no filler, but the first sentence is a long list of metrics that is somewhat dense. Both sentences earn their place; it is concise but slightly heavy in one breath.

  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?

  There is no output schema and no annotations, so the description must explain the return content and usage context on its own. It does so thoroughly, covering the comparison, projections, baseline reads, and the next race, making the tool's behavior sufficiently complete for correct invocation.

  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, so the baseline is 4. The description correctly avoids inventing parameter details and instead focuses on what the tool returns, which is the only relevant semantic content.

  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 ('Returns') and a clear resource ('this training week against the previous one'), then enumerates the exact metrics included. This distinguishes it from sibling per-metric getters like get_sleep_data, get_heart_rate_trends, and get_stress_levels.

  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?

  It explicitly states when to prefer this tool: when asked how the week or block is going, whether to back off, or what to do next week. It also contrasts it with reading individual metrics, giving an agent a clear decision rule for selection.

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