list_workouts

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

No annotations are provided, so the description carries the full burden — and it delivers. It declares read-only status, documents newest-first ordering, discloses automatic offset-based pagination, and adds critical field-level caveats: activityId is numeric with no plain-language sport field, energyConsumption is in joules not 'totalCalories', and hrdata.max is the account overall max HR rather than the workout peak (hrdata.workoutMaxHR). These are exactly the behaviors that would cause silent data misinterpretation if omitted.

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

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

The description is long (~130 words) but every clause earns its place: field enumeration with units, three disambiguation caveats that prevent wrong data interpretation, sibling routing, pagination semantics, and a read-only declaration. The core purpose is front-loaded in the first sentence, and the density is justified because each caveat prevents a distinct class of agent error. Nothing is filler.

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

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

With no output schema and no annotations, the description must document the return contract itself — and it does, listing all response fields with units (workoutKey, activityId, startTime, totalTime, totalDistance, totalAscent, totalDescent, energyConsumption, hrdata avg/max/workoutMaxHR). It covers pagination, ordering, read-only safety, and directs to siblings for missing detail. The only minor blemish is listing hrdata as '{ avg, max }' before referencing workoutMaxHR, but the caveat text resolves it; nothing critical is missing for correct invocation.

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

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

Schema description coverage is 100%, so the baseline is 3 and the schema already documents limit/since/until thoroughly. The description adds marginal but real value by explaining the offset-based pagination mechanism and its termination condition ('until limit is reached or no more workouts exist'), which clarifies how limit interacts with paging beyond the schema's 'Pagination is automatic' note. This nudges it above baseline without the description carrying the parameter documentation burden.

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

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

The opening sentence names a specific verb, resource, and scope: 'Returns the user's recent Suunto workouts ordered newest-first (Workout API v3).' It goes further than most by enumerating the exact response fields, which makes the tool unmistakable, and it explicitly distinguishes itself from get_workout (full detail on a single result) and get_workout_fit (sport name lookup). An agent could not confuse this with a sibling.

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

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

The description routes the agent to alternatives under specific conditions: 'use get_workout_fit for the parsed FIT file's session.sport if a sport name is needed' and 'Use get_workout for full detail (laps, HR zones, sport-specific metrics) on a single result.' It also explains when pagination stops ('until limit is reached or no more workouts exist'), giving the agent a clear decision procedure for list vs. detail calls.

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