read_coach_cohort

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description does add real behavioral context in the form of the min-3-people privacy threshold, medians-only aggregation, and the fact that it explains the reason when there is no data to show. It stops short of describing auth requirements or instance-scope 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?

Two sentences, front-loaded with the purpose and its privacy constraints, with the empty-result note trailing. Dense but every clause (medians only, three-people threshold, profile unit) adds information rather than padding.

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 zero-param read tool with no output schema, the description conveys what is returned (weekly sessions and lifts, as medians, in the profile unit) and handles the no-data case, which is what an agent needs. Exact field names and format are left unspecified, a minor gap.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing parameter-wise for the description to clarify or compensate for.

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 states a specific resource and content: community comparison of weekly sessions and lifts against other opted-in users on the instance. However it never names itself as a distinct tool or distinguishes it from similar read tools such as read_training_summary or read_coach, which also surface performance aggregates.

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?

Usage is implied by the privacy preamble (opted-in users, minimum of three people) and the note that it explains empty results, but there is no explicit statement of when to choose this over read_training_summary or read_coach, nor any exclusion guidance.

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