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

Annotations already declare this as a safe read, but the description goes well beyond them: data provenance (bests derived from the full-resolution import stream, matching the head unit), the meaning of the `pending` counter and how to phrase results that aren't final, and the fact that it also returns the threshold/battery/fade readings shown on the athlete's Records page.

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 core purpose and the two-window mechanics are front-loaded, and each paragraph carries distinct information. It is longer than needed in places (e.g., the aside about never quoting different numbers than the page), which slightly dilutes scannability but does not bury the key points.

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?

No output schema exists, so the description carries the full burden of describing return values, and it does: row contents, session provenance, the 90-day gap marker, the threshold/battery/fade readings, and the pending state. Nothing essential for calling or interpreting the result 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?

There is only one parameter, and the 100%-covered enum schema already documents it. The description adds real meaning by explaining what each enum branch yields (cycling: best average watts over 18 windows; running: fastest time over 12 distances with pace), though it does not add any parameter syntax beyond that.

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 specific verb+resource and the exact scope: the athlete's bests for one sport across the last-90-day and all-time windows, with per-sport peak definitions (18 power windows vs 12 run distances). It is clearly distinguishable from siblings like estimate_thresholds or get_metric_history without opening any 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?

Gives concrete when-to-use scenarios (anchor threshold estimates, spot a decayed top end, size interval targets, distinguish a true PR from a good day) and explains how to read the 90-day-vs-all-time gap. It also flags the `pending` > 0 caveat and routes the agent to the shared `howToRead` block used by estimate_thresholds.

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