Get Garmin activity streams

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

Annotations only declare readOnlyHint and openWorldHint=false, so the description carries the behavioral load and does so well: Garmin-side downsampling to roughly `points` rows, omission of channels the activity didn't record, exclusion of location data entirely, and the default channel set. It also fixes the row layout (distance in km then elapsed time in s), which an agent could not infer otherwise.

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 what the tool returns, then channel defaults, then the id prerequisite. Every sentence adds a fact an agent needs; nothing is redundant with the schema.

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, the description fully compensates by describing the return shape (`columns` and `rows`, leading distance/elapsed-time fields). For a three-parameter read tool with rich schema coverage and minimal annotations, 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 100%, so the baseline is 3; the description earns more by restating the default channel list and adding semantics the enum doesn't carry — that cycling activities should use speed rather than pace, and that unsupported channels are silently dropped rather than erroring. The `points` parameter's downsampling behavior is also characterized as approximate, matching the schema's "Approximate number of rows."

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?

States a concrete verb+resource: time series for one activity, downsampled to about `points` rows, with illustrative questions ("did my HR drift in the last 10 km?") that make the output type unambiguous. It implicitly distinguishes itself from summary-style siblings like garmin_get_activity, though it never names garmin_get_activity_laps, the closest sibling by granularity.

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?

Clear usage context is conveyed through the two example questions and the explicit prerequisite "Get the activity id from garmin_search_activities," plus a selection rule for channels ("Use speed instead of pace for cycling"). It lacks explicit when-not guidance, e.g. pointing to garmin_get_activity for summary stats or laps for per-lap splits.

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