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

Annotations cover the safety profile (readOnly, idempotent, openWorld), but the description adds the crucial non-obvious trait that this is an asynchronous background run requiring a second call with the same domain to poll for results, plus a latency warning ('Slow'). That is real behavioral value beyond the annotations, though it omits how long the run takes or how to detect readiness.

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?

Sentences are front-loaded and each earns its place: purpose, then result, then async behavior, then the alternative, then a docs link. The only mild weakness is deferring 'how the questions are chosen and how to read the result' to an external URL rather than stating it inline.

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 single-parameter tool with annotations and no output schema, the description covers purpose, async flow, the alternative tool, and roughly what the result contains. It is nearly complete, missing only timing/readiness detail for the polling loop.

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 schema already defines 'url' as 'The domain to audit', so the baseline is 3. The description adds meaning beyond the schema by revealing the url doubles as a run key that must be re-supplied to collect the result, which is genuinely informative for correct invocation.

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 verb and resource (runs 5 buying questions through ChatGPT to audit AI visibility) and names exactly what the agent learns back (brand presence, winning competitors, shaping sources). It is clearly distinguishable from siblings like audit_site and track_question.

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?

It explicitly gives the when-to-use condition ('Slow: it starts a background run and you call it again with the same domain to collect the result') and names the alternative with its selecting condition ('Use audit_site for anything that needs an answer now'). Nothing is left to inference.

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