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

Annotations only declare readOnlyHint=true; the description goes well beyond that by disclosing the output nature (aggregated category counts, no raw rejection text), the privacy guarantee, and how the result should be interpreted relative to client-specific data. That is rich behavioral context an agent could not infer from structured fields.

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 purpose, then weighting guidance, then precedence rule. Three sentences that each carry information, though the interpretation guidance could be slightly tighter.

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, and the description does cover the return shape (category counts) and the read-only nature. The only real gap is the sinceDays parameter's meaning, which is left entirely to the schema.

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 one parameter (sinceDays) with 0% schema description coverage, and the description never names it or explains its window; 'recently' only loosely gestures at the time range. With an undocumented parameter, the description should compensate but does not.

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 (check) and resource (platform-wide coach rejection trends) and clarifies the return shape: 'as category counts (never any client's raw rejection text)'. It explicitly contrasts itself with get_client_ai_history, so an agent can distinguish it from the sibling without opening either 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 explicit when/when-not guidance: use as a 'secondary caution alongside get_client_ai_history, not a hard constraint', apply the 30%-dominance heuristic, and defer to the client's own data. Nothing is left to inference about how to weight the signal.

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