get_activity_details

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

With no annotations, the description carries the full burden and delivers: it discloses the return contents (lat/lon/altitude/time/distance/speed, bounding box, start/end), the server-side downsampling behavior ('at most max_points, evenly spread ... shape survives at any size'), and the indoor-activity edge case where no track exists but metric keys are still listed. This is exactly the kind of behavioral context annotations would otherwise provide.

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 action, then returns, then alternatives, then args — a logical order with no filler sentences. It runs longer than strictly necessary (returns could be leaned on the output schema), but each section adds distinct value, so it stays efficient rather than padded.

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?

Given a mutation-free read tool with an output schema and a 2-param schema lacking descriptions, the definition covers everything an agent needs: purpose, alternatives, return shape, downsampling semantics, param defaults, and the no-GPS edge case. Nothing material is missing.

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 coverage is 0%, so the description must compensate, and it does: activity_id is defined as 'ID of the activity to retrieve the track for,' and max_points gets its default (500), its meaning (max track points returned), and actionable guidance to raise it (~4000) for finer traces on long routes. No parameter is left undocumented.

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 verb+resource ('Get the GPS track and per-point route data for an activity') and immediately names the siblings it is not (get_activity, get_activity_fit_data), stating its distinct niche: 'this tool is for the route itself.' An agent can route to it without opening a schema.

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?

Explicitly names two alternatives and what each is for ('get_activity for the summary metrics', 'get_activity_fit_data for full per-second sensor series'), then lists concrete use cases (mapping, course analysis, locating a climb or interval). When-to-use and when-not-to-use are both covered.

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