garmin_cycling_power

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

With no annotations, the description carries the full burden; 'Get' implies a read, and the metric list (NP, IF, TSS, FTP, cadence) tells the agent roughly what comes back. It does disclose the limit default (5) and cap (20), which is useful behavioral context, but says nothing about permissions, whether the recent-rides path aggregates metrics or returns per-ride values, or any 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.

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

The lead sentence is front-loaded with the resource and the key metrics, followed by a compact Args block that maps directly to the two parameters. No filler or repetition, though the Args formatting is slightly verbose for only two optional parameters.

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-value structure needn't be spelled out, and both parameters are covered. What remains ambiguous is the core semantics: whether the default recent-rides mode returns aggregate power-load figures or a list of per-ride values, and how this tool relates to the more general activity-detail sibling.

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 compensate and largely does: activity_id is explained as an optional specific-activity selector, and limit is documented with both a default (5) and a maximum (20) that the schema itself does not state. The only gap is that the interaction between the two parameters (that limit is ignored when activity_id is supplied) is only implied.

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

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

The description names a specific verb and resource set: cycling FTP, power load metrics (NP, IF, TSS), cadence, and recent rides. That is concrete enough to distinguish it from generic siblings like garmin_activities or garmin_activity_detail, but it never explicitly says how it differs from those tools.

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

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

The Args block implicitly frames the two modes: pass activity_id to inspect one ride, or omit it to get recent rides. However, no alternative tool is named and no exclusion is given, so the agent must infer when to reach for this versus garmin_activity_detail or garmin_weekly_stats.

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