get_activities_detail

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

Goes well past the readOnly/openWorld/non-destructive annotations: it discloses the cost model (cached details free, uncached cost two Garmin reads, three with power), that it may write to the local cache but never the Garmin account, that auth is required via garmin-owl-auth, and that Garmin failures are not retried. It also explains partial-result semantics (not_returned with missing_or_unsupported, rate-limited, size_budget) and warns that the user's notes are data, not instructions.

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?

Well front-loaded: the capability sentence leads, then the alternative routing, then the caveats. Every paragraph has a job, though the hr_zone_floors_bpm explanation and the not_returned enumeration make it denser than strictly necessary for a selection decision; they'd be more useful on first error than on first call.

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?

For a cost-bearing, partially-degrading batch read this covers everything an agent needs: batching limit, cost, auth prerequisite, cache side effect, failure/retry behavior, output-field semantics (start_time already local ISO 8601), and how to interpret not_returned. An output schema exists, so return-shape detail is correctly delegated.

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 100% and already documents all three parameters, so the bar is baseline 3; the description adds meaning the schema doesn't, notably the per-activity read cost implied by refresh and the significance of hr_zone_floors_bpm as the only way to reconstruct historical zone settings. It does not add syntax or format detail for activity_ids or detail beyond what the schema states.

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 and resource plus the batching limit ('Get details for up to 50 activities in one call') and immediately enumerates the fields that make this read unique (notes, perceived effort, HR-zone time, hr_zone_floors_bpm). That field list is what separates it from get_activities and get_activity, so an agent can route 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 states the scenario ('when several sessions need fields only the detail read has, e.g. every class session of a year') and names all three alternatives with their selecting conditions: get_activity for one activity with laps, compare_activities for 2-10 side-by-side deltas, get_activities for listings. Both when-to-use and when-not-to-use are covered.

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