get_fitness_trends

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

Annotations already declare readOnly/no-destructive/closed-world, and the description adds real behavioural context beyond them: the change is computed from the first month to now, each marker is classified improving/steady/declining, and the missing-data case is specified ('With no weigh-ins logged, say so and that weighing in through Garmin Connect or a Garmin scale is what fills it'). That is the kind of edge-case disclosure agents need to avoid fabricating weight trends.

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?

Front-loaded with the core purpose and the marker list before the usage guidance, and every clause carries information. It runs long however — dense multi-line paragraphs plus a quoted-phrasings list and response-format instructions — which costs some scannability for an agent parsing quickly.

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?

An output schema exists, so return shape need not be explained, and the description still covers the main edge case (no weigh-ins) and routing to siblings. The remaining gap is the case of no fitness-marker data at all (e.g. a device that never recorded VO2 max), which the description does not address.

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 0%, so the description must carry the parameter, and it does: the 'Args' block states the range 1-12, the default of 6, and the non-obvious nuance that the window is inclusive of the current month. No ambiguity remains about what 'months' means.

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?

Opens with a specific framing ('Whether the user is getting fitter') and then enumerates exactly what is returned: VO2 max, race predictions, lactate threshold, endurance/hill score, cycling FTP, plus weight/body composition, each as a monthly value with change since the first month. It explicitly contrasts itself with siblings ('For where they stand today, get_fitness is enough'), so an agent can distinguish it without opening schemas.

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?

Names concrete triggering questions ('am I getting fitter', 'is my VO2 max going up', 'was I faster when I was lighter') and gives explicit alternatives with conditions: get_fitness for today's snapshot, get_recovery_trends for recovery. It also prescribes the analysis pattern (name markers that moved and by how much; correlate weight with markers as pattern not cause).

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