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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the enumerated status values, what data arrives when done, the ~20 second internal wait, and the fact it won't launch a check. This is exactly the extra behavioral detail the structured fields cannot convey.

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?

Five sentences, all front-loaded around the core action first, then return semantics, then polling behavior, then the negative constraint. Every sentence carries distinct information with no 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?

With no output schema, the description carries the return-value burden and does so fully, enumerating statuses and the completion payload (counts, competitor names, one fix). Nothing an agent needs to call or interpret this tool 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% and the single check_id parameter is fully documented there, so baseline is 3. The description adds value by tying the parameter to its producer (the check_id returned by check_ai_recommendation), clarifying origin rather than repeating the schema.

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 (read) and resource (the result of a check), names the sibling that creates it (check_ai_recommendation), and explicitly disambiguates by saying it does not start a new check. An agent can distinguish it from its sibling immediately.

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 the precise precondition (use the check_id returned by check_ai_recommendation) and the polling protocol: while queued/running, poll_after_s is the suggested wait. It also rules out the alternative action ('does not start a new check'), leaving nothing to inference.

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