Server Quality Checklist

Tool Scores

• garmin_personal_recordsB
  3.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the tool's safety and side-effect profile. The description adds minimal behavioral context—mentioning return format (markdown or json) and error output—but does not expand beyond what annotations imply. With strong annotation coverage, a score of 3 is appropriate.

  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 concise with two sentences, front-loading the purpose. The Args/Returns section provides additional structure, though the formatting is slightly informal. Overall, it is efficient without unnecessary words.

  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?

  Given that annotations cover safety and idempotency, and an output schema exists, the description is fairly complete. It specifies the return content ('lista de records con tipo, valor y fecha') and format options. However, it could be more explicit about the exact types of personal records included.

  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%, yet the description only clarifies the response_format parameter by listing its allowed values ('markdown|json'), which are already defined as an enum in the schema. It does not describe the inner structure of the 'params' object or provide any additional semantics beyond the schema. This is insufficient compensation for the lack of schema descriptions.

  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's purpose: listing personal records from Garmin ('mejores marcas'). The verb 'Lista' is specific, and the resource 'records personales de Garmin' distinguishes it from sibling tools like garmin_race_predictions or garmin_get_activities, though it could be more precise about the types of records.

  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 provided on when to use this tool versus alternatives. The description does not mention scenarios, prerequisites, or compare with sibling tools such as garmin_get_activities or garmin_race_predictions.

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

• garmin_fitness_metricsB
  3.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to restate safety. However, it adds no additional behavioral details like data source, syncing requirements, or rate limits.

  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 short and front-loaded with the metric names. It includes an args section and returns section, making it well-structured. However, it could be slightly more concise by avoiding repetition.

  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?

  Given the annotations and existing output schema, the description is adequate but lacks contextual details such as that data comes from Garmin Connect, potential latency, or conditions for missing data. It does not fully explain parameter behavior beyond basic syntax.

  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 description reiterates the parameters (date and response_format) with brief explanations, but these are already covered by the input schema (defaults, patterns, enum). With 0% schema description coverage, the description adds minimal value 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 clearly identifies the tool's output: VO2max for running and cycling, and fitness age from Garmin. It distinguishes among siblings by specifying unique metrics, though it lacks an explicit verb like 'get' or 'retrieve'.

  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 alternatives, such as other Garmin metric tools (e.g., garmin_hrv, garmin_sleep). The description does not provide context or exclusions.

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

• garmin_race_predictionsA
  3.7/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds relevant behavioral context by specifying the return format (markdown/json) and the possibility of an error string, which is sufficient.

  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 concise (two sentences plus args section) and front-loaded with the key purpose. However, it could be slightly better structured (e.g., bullet points for distances) but remains efficient.

  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?

  Given the tool's simplicity (one parameter, clear annotations, and output schema), the description adequately covers the necessary context: distance types, return format, and error handling. It is complete for its complexity level.

  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 defines the 'response_format' parameter with an enum and a description ('markdown o json'). The tool description merely repeats this information without adding further semantic value beyond what the schema provides.

  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 explicitly states 'Predicciones de tiempo de Garmin para 5K, 10K, media maraton y maraton', which clearly communicates the specific verb (predicciones) and resource (tiempo) for distinct distances, making it easily distinguishable 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 Guidelines2/5

  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 like garmin_personal_records or garmin_fitness_metrics. The description implies usage through the name but lacks explicit context or exclusion criteria.

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

• garmin_training_statusA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds that the tool returns a dict or error string but does not disclose any additional side effects, authorization needs, or rate limits beyond what annotations provide.

  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 two paragraphs with a concise first line listing metrics. It is front-loaded with the purpose and efficiently lists parameters. No unnecessary sentences.

  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?

  Given the existence of an output schema (context signal), the description need not detail return structure. It covers the main function, parameters, and return type (str: dict or error). No missing elements for a simple data retrieval tool.

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

  Parameters4/5

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

  The schema has 0% coverage for the top-level 'params' parameter, but nested parameters (date, response_format) are described. The description repeats these parameter details (format, defaults) and adds context about their meaning, compensating for the schema's lack of top-level 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?

  The description clearly states the tool gathers training status, acute/chronic load, VO2max, endurance score, and hill score. The verb 'reune' (gathers) specifies a read operation, and the list of metrics distinguishes the tool from siblings like garmin_fitness_metrics, though not explicitly.

  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 use this tool versus related tools like garmin_fitness_metrics or garmin_daily_readiness. It lacks any mention of conditions, prerequisites, or alternatives.

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

• fitness_recovery_vs_trainingA
  3.9/5.0
  Behavior3/5

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

  Annotations already indicate the tool is read-only, idempotent, and non-destructive. The description adds that it requires Apple data for recovery and returns a table or error string. It does not contradict annotations but also does not elaborate on behavior beyond what annotations convey.

  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 concise and front-loads the main purpose. The parameter list follows clearly. One could argue for slightly more structure, but it remains efficient without wasted words.

  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's purpose, inputs, output format, and prerequisites are covered. The 'Returns' line specifies a table by day or an error, which is adequate given no output schema. However, it could detail the output columns for greater completeness.

  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 description repeats parameter names and formats already documented in the input schema. With schema coverage effectively high (the schema includes descriptions for start, end, and response_format), the description adds no new semantic meaning.

  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's purpose: to cross-reference daily training data from Garmin and Apple with recovery metrics (HRV, sleep, resting HR). The verb 'Cruza' (cross) and the specific resources (training + recovery) make it distinct from sibling tools that focus on individual metrics.

  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 concrete use cases (correlating HRV drops after hard days, worse sleep after strength days) and a prerequisite (Apple data imported). It implies when to use this tool over others, though it does not explicitly list alternative tools for specific purposes.

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

• garmin_daily_readinessA
  3.9/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and destructiveHint=false. Description adds detailed return fields (readiness_score, fc_reposo, etc.) and context about the data source (Garmin daily readiness). No contradictions; adds value 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.

  Conciseness4/5

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

  Description is concise with a brief introductory sentence followed by structured Args and Returns sections. No unnecessary words, though the Args section could be integrated into the prose.

  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 tool's purpose, required input (date), output format options, and lists return fields. It is complete for a read-only tool with output schema (though output schema not shown). Error handling is minimally mentioned ('Error: ...').

  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 0% (tool description does not document parameters beyond what schema provides). However, the description does mention date format and response_format options, repeating schema info without adding new semantics. 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?

  Description clearly states it summarizes daily recovery metrics (training readiness, HRV, sleep, etc.) using specific verbs like 'Resume la recuperacion de un dia'. It distinguishes from sibling tools like garmin_sleep or garmin_hrv by being a comprehensive daily readiness summary.

  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?

  Implies usage ('La herramienta clave para decidir si empujar o descansar') but does not explicitly state when to avoid or mention alternative tools among the 21 siblings, such as garmin_training_status or fitness_recovery_vs_training.

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

• garmin_get_activitiesA
  4/5.0
  Behavior3/5

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

  Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that it returns a string with a list of activities or an error, and explains the response format parameter. However, it does not disclose ordering (likely most recent first) or any potential pagination/rate limits. Contributes some value beyond annotations but 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.

  Conciseness5/5

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

  The description is concise and well-structured, using a clear docstring format with Args and Returns sections. Every sentence adds essential information without redundancy.

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

  Completeness4/5

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

  For a simple listing tool with two parameters and annotations providing safety clues, the description is fairly complete. It explains the purpose, parameters, and return format. However, it lacks mention of ordering (likely most recent first) and any default behavior, which would improve completeness. An output schema exists but is not shown; the description states return type as string, which is sufficient.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It explicitly lists the arguments: limit (1-50) and response_format (markdown|json), adding constraints and enum values. This clarifies the parameters beyond the schema. Could mention defaults (limit=10, response_format=markdown) which are in schema but not in 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?

  The description clearly states that the tool lists the latest registered activities with summarized metrics. It specifies the verb (list), resource (activities), and scope (summarized metrics). This distinguishes it from siblings like garmin_get_activity, which retrieves a single activity.

  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?

  No explicit guidance on when to use this tool vs alternatives. The description implies it's for listing recent activities, but does not mention when not to use it or provide alternative tool suggestions. The sibling tools are varied, so more context would help an AI agent decide.

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

• garmin_get_activityA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, indicating a safe read operation. The description adds minimal behavioral context (e.g., possible error format) but does not disclose rate limits, data freshness, or permissions. Since annotations are rich, the description adds only marginal value.

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

  Conciseness5/5

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

  The description is concise with a clear docstring structure (Args/Returns). It is front-loaded with the core purpose and uses minimal sentences without redundancy.

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

  Completeness4/5

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

  Given the tool has one required parameter and an output schema, the description provides a sufficiently complete overview of inputs and outputs. However, it does not mention the language (Spanish) which might confuse non-Spanish agents, and it omits handling of optional parameters beyond the default.

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

  Parameters4/5

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

  Schema description coverage is 0% for parameters, so the description must compensate. It lists activity_id and response_format with valid values (markdown|json) and explains returned metrics (distancia, duracion, etc.). This adds meaningful context beyond the schema, though the description could be more explicit about the enum values for response_format.

  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 details of a specific Garmin activity, using a specific verb and resource. It distinguishes from sibling tools like garmin_get_activities (which lists activities) by focusing on a concrete activity.

  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 when you have a specific activity_id, but it does not explicitly state when to use this versus alternatives like garmin_get_activities or garmin_activity_splits. No when-not-to-use guidance is provided.

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

• garmin_delete_workoutA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare destructiveHint=true. The description adds the behavior that deletion only occurs when confirm=True, and that without confirmation it returns a warning. This goes beyond the annotations by specifying the safety mechanism.

  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 brief and includes sections (main, SEGURIDAD, Args, Returns). It is not overly verbose, though the Args section could be omitted as the schema already defines parameters.

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

  Completeness4/5

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

  The description covers the return type (confirmation or error message) and the safety confirmation. For a simple delete tool, this is adequate. It could mention error cases (e.g., workout_id not found) but the given information suffices.

  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 0% per context (though schema has descriptions), so baseline is 3. The description merely lists parameter names and types without adding semantics beyond what the schema provides.

  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 explicitly states the verb 'Borra' (delete) and the resource 'entreno guardado de tu biblioteca de Garmin', clearly distinguishing it from sibling tools like garmin_list_workouts (list) and garmin_schedule_workout (create).

  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 highlights a critical safety guideline: 'requiere confirm=True. Sin confirmacion no borra nada.' It implicitly tells when to use (delete) but does not provide explicit exclusions or alternatives. However, the context of sibling tools makes the usage clear.

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

• garmin_pace_zonesA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, indicating a safe read operation. The description adds behavioral context: it calculates zones using the classic 5-zone model based on threshold pace, and returns the threshold used and zone ranges. 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.

  Conciseness4/5

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

  The description is concise, front-loaded with purpose, and includes parameter hints and return info. It is efficiently structured with minimal waste, though slightly verbose with the 'Args:' and 'Returns:' formatting.

  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?

  Given the richness of annotations and input schema, the description adequately covers the tool's purpose, parameters, and return value. It explains the fallback behavior and output format, making it complete for an AI agent.

  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 provides descriptions for parameters (threshold_pace format and default behavior, response_format enum). The tool description repeats this info and adds a brief summary. Since schema coverage is good, the description adds marginal value.

  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 purpose: estimating running pace zones (Z1-Z5) from threshold pace. It specifies that it uses provided threshold_pace or reads from Garmin lactate threshold, effectively differentiating from sibling tools like garmin_hr_zones.

  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 when to use the tool: provide threshold_pace or omit to auto-fetch from Garmin. It does not explicitly mention when not to use or compare with alternatives, but the context is clear.

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

• fitness_daily_briefA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true, establishing safety and non-destructiveness. The description adds value by noting data aggregation from Apple with Garmin as fallback, and that output is a string. 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.

  Conciseness5/5

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

  The description is extremely concise: two sentences plus an Args/Returns section. It is front-loaded with the core purpose and efficiently conveys all essential information without 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?

  Given the tool's moderate complexity as an aggregator, the description covers key aspects: data sources, components retrieved, and return format. It does not detail error handling or missing data scenarios, but these are minor gaps. Overall sufficiently complete for a read-only summary 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?

  The description does not mention parameters, but the input schema provides clear descriptions for both 'date' (format and default) and 'response_format' (enum with defaults). With schema covering parameter semantics adequately, a baseline of 3 is appropriate despite zero description coverage.

  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 provides a morning brief summarizing recovery (HRV, sleep, resting HR from Apple with Garmin backup), yesterday's training, and today's planned workouts. It distinguishes itself from individual Garmin data tools and other composite summaries, making the purpose unmistakable.

  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 using this tool for a consolidated morning brief instead of calling multiple individual tools. However, it lacks explicit when-to-use or when-not-to-use guidance, and does not name alternatives directly. Context is clear but not fully prescriptive.

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

• fitness_profileA
  4.2/5.0
  Behavior4/5

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

  Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) indicate a safe read operation. Description adds context that values come from .env and are defaults for zone tools, reinforcing behavior without contradiction.

  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?

  Description is 4 lines, front-loaded with purpose, then usage context, then parameter and return info. Efficient but slightly verbose. No wasted sentences.

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

  Completeness5/5

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

  Given the tool's simplicity and presence of output schema, description sufficiently covers input, behavior (reads from .env, returns profile or warning), and relationship with sibling tools. No obvious gaps.

  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?

  Only one parameter 'response_format' with enum. Schema already describes it as 'markdown o json' with default 'markdown'. Description repeats this without additional semantics beyond what schema provides. Schema coverage is 0% per context, but the schema description is functional.

  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 clearly states 'Muestra el perfil configurado' (shows configured profile) listing specific fields (FCmax, FC reposo, edad, ritmo umbral). This is a specific verb and resource, and it distinguishes from sibling Garmin and fitness tools by focusing on local environment variables.

  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?

  Explains that these values are defaults used by zone tools when not explicitly provided, implying when to check/use this tool. It does not explicitly state when not to use it, but the context is clear enough.

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

• garmin_sleepA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, indicating safe, non-destructive behavior. The description adds transparency by detailing the output structure (hours total, phases, score, optional heart rate/respiration) and mentions error handling with 'Error: ...'. This goes beyond what annotations convey.

  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 extremely concise: a one-line purpose followed by clear Args and Returns sections. Every sentence adds value, no redundancy. Front-loaded with the core function.

  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?

  Given the tool's simplicity (single date, sleep data), the description covers output structure and error cases. Although an output schema exists, the description explains the return values adequately. It could mention behavior for missing data or date ranges, but overall it is complete for the intended use.

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

  Parameters4/5

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

  Despite the schema having parameter descriptions, the context notes 0% schema description coverage, so the description must compensate. It explicitly lists the parameters: date (YYYY-MM-DD) and response_format (markdown|json), matching the schema and clarifying their types. The return description further enriches understanding of how parameters affect output.

  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 it provides a breakdown of a night's sleep including phases, total duration, and score. The title 'Desglose de sueño (Garmin)' reinforces this. The sibling tools are distinct (readiness, activities, HRV, etc.), so there is no confusion about its purpose.

  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 implicitly indicates it is for querying sleep data for a single night, but it does not explicitly state when to use this tool versus alternatives like garmin_daily_readiness or fitness_daily_brief that may also include sleep metrics. No exclusion criteria or context switching guidance is provided.

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

• garmin_hrvA
  4.3/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, idempotentHint=true, etc. Description adds valuable context: return includes weekly average, status, and base range, plus warning if device lacks HRV data. 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?

  Very concise: one-liner purpose plus structured Args/Returns block. Every sentence is informative with 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?

  Given the tool's simplicity, annotations, and output schema, the description covers return structure, failure mode, and parameter details adequately.

  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 0%, but description explains date format (YYYY-MM-DD) and response_format options, adding meaning beyond the schema's regex and enum.

  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 it retrieves HRV data for a specified night, with parameter details and return structure. It distinguishes from sibling tools like garmin_sleep or garmin_hr_zones by focusing on HRV.

  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?

  Usage is implied (for HRV data), but no explicit guidance on when to use this vs. alternatives like garmin_hr_zones or garmin_daily_readiness. No exclusions or context provided.

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

• garmin_list_workoutsA
  4.3/5.0
  Behavior3/5

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

  Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. Description adds no additional behavioral traits beyond listing workouts, so it does not significantly improve transparency beyond what annotations already 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?

  Very concise: one sentence for purpose, one sentence for usage context, then clear Args and Returns sections. No wasted words, 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?

  Covers purpose, usage context, parameters, and return format adequately. Lacks details on ordering or error messages beyond a generic 'Error: ...', but annotations and output schema (present per context) likely fill gaps. Minor omission of pagination behavior, but limit parameter implies a capped list.

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

  Parameters5/5

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

  Despite schema description coverage being 0% (per context), the description explicitly lists parameters with their valid ranges (limit 1-100) and options (response_format markdown or json), fully compensating for the lack of schema 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?

  Describes clearly that the tool lists saved workouts with their IDs, and mentions its utility for obtaining workout_id for scheduling or deletion. Distinguishes from sibling tools by specifying the resource (saved workouts) and linking to specific dependent 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?

  Explicitly states when to use this tool (to get workout_id for schedule or delete), providing clear usage context. Does not mention when not to use or alternatives, but context is sufficient.

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

• fitness_body_compositionA
  4.4/5.0
  Behavior4/5

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

  Beyond the annotations (readOnly, idempotent, non-destructive), the description reveals it reads from Garmin and Apple Health, shows per-date values plus trend (difference between first and last), and expects monthly usage. 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.

  Conciseness4/5

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

  The description is concise, with a clear purpose paragraph and structured Args/Returns section. While slightly informal and in Spanish, it is efficient and front-loaded.

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

  Completeness5/5

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

  Given the tool's complexity (two data sources, trend calculation) and absence of an output schema, the description fully explains what data is returned (series by date, trends for weight/fat/muscle) and error handling. It covers all necessary context for an AI to use it correctly.

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

  Parameters4/5

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

  With schema description coverage at 0%, the description compensates well by explaining start (YYYY-MM-DD), end (optional, defaults to start+6 days, but suggests wide range), and response_format. This adds clear meaning beyond the schema's bare 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 clearly explains the tool tracks evolution of weight, fat %, and muscle mass over a period, combining data from Garmin and Apple Health. It specifies monthly tracking vs daily weighing, distinguishing it from siblings like garmin_add_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 Guidelines4/5

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

  Description states it is designed for monthly tracking—not daily weighing—and recommends a wide date range (e.g., 3 months) for trend analysis. However, it does not explicitly name alternative tools 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.

• garmin_activity_splitsA
  4.5/5.0
  Behavior5/5

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

  Las anotaciones ya indican que es solo lectura, idempotente y no destructiva. La descripción añade detalles sobre el comportamiento según la configuración de vueltas (auto-lap vs. manual) y el formato de retorno, sin contradecir las anotaciones. Esto da una transparencia completa.

  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?

  La descripción es concisa: un párrafo inicial con propósito y detalle conductual, seguido de 'Args' y 'Returns' en formato claro. No hay oraciones redundantes y la información esencial está al inicio. Muy bien estructurada.

  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?

  Para una herramienta simple (1 parámetro requerido, opcional de formato), la descripción cubre el propósito, el comportamiento con auto-lap, el formato de retorno (lista de splits con campos) y errores. Aunque no se muestra el esquema de salida, la descripción lo especifica. Es completa para su complejidad.

  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?

  La cobertura de descripción del esquema es 0%, por lo que la descripción del tool debe compensar. Solo repite los nombres y tipos de los parámetros ('activity_id (str)', 'response_format (markdown|json)'), sin añadir significado más allá de lo que ya está en el esquema. No explica el valor por defecto ni ejemplos de uso, por lo que es solo marginalmente útil.

  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?

  El verbo 'Devuelve' seguido del recurso 'vueltas (laps) de una actividad' especifica claramente la acción y el objeto. La descripción distingue el propósito de otros hermanos (como 'garmin_get_activity') al enfocarse en parciales por km, y explica casos límite como auto-lap o ausencia de vueltas.

  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?

  La frase 'Util para ver como dosifico un corredor' da una guía de uso en contexto. La nota sobre auto-lap ayuda a saber cuándo los datos serán por km. Sin embargo, no contrasta explícitamente con herramientas hermanas ni dice cuándo no usarla, aunque la especificidad lo hace útil.

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

• garmin_add_body_compositionA
  4.5/5.0
  Behavior5/5

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

  Discloses default dry_run safety behavior, which annotations do not provide. Notes it writes to Garmin. 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?

  Efficiently structured: purpose, context, safety, args list. Each sentence adds value.

  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?

  Covers use case, safety, relation to sibling, and return format. Adequate given rich schema and output description.

  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 already provides detailed parameter descriptions. Tool description lists params with optional markers but adds no new 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?

  Clear verb 'Guarda' and resource 'medicion de peso y composicion corporal en Garmin Connect'. Distinguishes from siblings like fitness_body_composition (read) by stating its write function.

  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?

  Explicit use case: when scale doesn't sync. Mentions safety dry_run but lacks explicit when-not-to-use or alternatives.

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

• garmin_hr_zonesA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and idempotentHint. The description adds substantial behavioral details: max HR derivation priority, use of Karvonen or %FCmax, e-bike caveat, and explicit statement that it does not write to Garmin. These go beyond annotations, though the description could mention that it may need recent activity 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?

  The description is well-structured: purpose first, then algorithm, caveats, usage note, and finally args/returns. Every sentence provides useful information; no redundancy. Front-loaded with the core action.

  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 complexity (multiple methods, fallbacks, caveats), the description covers all necessary aspects: algorithm, parameter roles, return format, and important notes (no writing to Garmin). Combined with rich schema descriptions and annotations, it is 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?

  Each parameter has a description in the input schema (e.g., age: 'Edad, para estimar FCmax...'). The tool description repeats some but also explains the overall algorithm, giving context (e.g., why max_hr is optional and how it influences the calculation). This adds value beyond the individual parameter 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 clearly states 'Estima tus zonas de frecuencia cardiaca (Z1-Z5)', specifying the action (estimates) and resource (HR zones). It distinguishes from siblings like garmin_pace_zones (pace zones) and explicitly notes it does not write to Garmin, setting it apart from write 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 explains the algorithm and caveats (e.g., e-bike limitation) and notes the tool is read-only. However, it does not explicitly mention when to use this tool over other Garmin tools, though the context makes it clear this is the only HR zone estimator.

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

• fitness_weekly_summaryA
  4.6/5.0
  Behavior4/5

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

  Adds value beyond annotations by clarifying that the tool returns a string summary or error message, and explains the default date range logic. Annotations already indicate read-only, idempotent, non-destructive behavior; description complements this with operational details.

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

  Conciseness5/5

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

  The description is concise and well-structured: a clear one-sentence summary, a technical prerequisite, then an explicit Args list, and a Returns line. Every sentence is informative with 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?

  For a tool that returns a string summary, the description covers purpose, prerequisites, parameters, and output format. Despite having an external output schema, the description self-contains return type information, making it fully complete for selection and invocation.

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

  Parameters5/5

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

  Although schema coverage is listed as 0%, the description actually explains all parameters in the Args section: start (format), end (optional with default behavior), and response_format (markdown/json). This adds significant clarity beyond the schema's simple type constraints.

  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 clearly states it generates a weekly summary of training and recovery by combining Garmin and Apple data. It specifies the data sources (activities, km, hours from Garmin; sleep, HRV, resting HR, steps, strength from Apple), setting it apart from siblings that only focus on one source.

  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 states that Apple data import is required for the recovery part, giving a clear condition for proper usage. However, it does not mention alternative tools among siblings for when Apple data is unavailable.

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

• fitness_planned_vs_actualA
  4.7/5.0
  Behavior5/5

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

  The description reveals important behavioral details: planned includes only scheduled structured workouts, cross is by day, and outputs include adherence percentage. Annotations already declare read-only, idempotent, non-destructive, and the description adds context beyond those.

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

  Conciseness5/5

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

  The description is concise and well-structured with clear sections for explanation, arguments, and returns. Every sentence adds value with 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?

  Given the simple input schema and presence of output schema, the description covers all necessary aspects: return format, adherence calculation logic, and detailed output description, making it 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?

  The description adds meaning to parameters by explaining date formats (YYYY-MM-DD) and the response_format enum values, which are already in the schema. It also contextualizes the parameters within the tool's logic.

  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 compares planned vs actual workouts and calculates adherence. It distinguishes from siblings like garmin_get_activities or fitness_weekly_summary by focusing specifically on plan adherence.

  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 tool is used for comparing planned and actual workouts in a date range. While it does not explicitly mention alternatives, the context of siblings makes its unique purpose clear.

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

• garmin_schedule_workoutA
  4.7/5.0
  Behavior5/5

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

  La descripción revela comportamientos clave más allá de las anotaciones: que por defecto es dry_run (no escribe) y que para crear realmente se debe pasar dry_run=False. También especifica lo que devuelve en cada caso (previsualización vs. workout_id). No contradice las anotaciones.

  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?

  La descripción es concisa y bien estructurada: encabezado con la acción principal, luego advertencia de seguridad, luego detalles de pasos y argumentos, y finalmente lo que retorna. Cada frase aporta información útil sin redundancia.

  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?

  Para un herramienta compleja con pasos anidados y objetivos opcionales, la descripción cubre todos los aspectos: cómo definir pasos, objetivos por deporte, formato de fecha, parámetros de salida (preview vs. confirmación). Con el esquema y la salida existentes, es completa para que un agente la use.

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

  Parameters4/5

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

  Aunque el esquema tiene descripciones detalladas de los parámetros (la cobertura es alta), la descripción agrega valor al explicar los objetivos deportivos específicos (FC, ritmo, potencia) y la seguridad del dry_run. La descripción compensa la dependencia del esquema.

  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?

  La descripción comienza con una acción específica: 'Crea un entreno estructurado y lo programa en una fecha del calendario de Garmin'. Esto distingue claramente el propósito de otros hermanos como garmin_list_workouts (listar) o garmin_delete_workout (eliminar). El verbo y el recurso están bien definidos.

  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?

  La descripción incluye una advertencia de seguridad sobre el dry_run, explicando cuándo usar dry_run=False para escribir realmente. También detalla los pasos y objetivos por deporte. Sin embargo, no menciona alternativas entre los hermanos ni cuándo no usar esta herramienta.

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