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

Beyond the annotations (readOnlyHint/idempotentHint/openWorldHint), the description discloses the key behavioral traits an agent needs: this is a slow, asynchronous background run that must be re-invoked with the same domain to retrieve results, and it takes a few minutes. That poll-and-collect contract is exactly the kind of context annotations cannot express.

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?

Three short sentences, front-loaded with what the tool does, then latency/async behavior, then the sibling alternative. Nothing is wasted for a tool of this complexity. The first sentence leans slightly on marketing phrasing, which slightly softens the otherwise tight structure.

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?

There is no output schema, so the description carries the burden of explaining results; it sketches the return ('shows you who gets named') without detailing the report structure. Combined with the async polling guidance and the alternative-tool pointer, an agent has enough to invoke and collect correctly, though the result shape remains somewhat abstract.

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 'url' parameter is already documented as 'The domain to audit,' so the baseline is 3. The description adds meaningful semantics by stating you call it again with the same domain to collect the result, clarifying that the argument doubles as a stable run key rather than just a one-shot input.

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 what the audit produces: 10 real buying questions about the user's category and who gets named in the answers. It reads somewhat like product copy ('Peak Answer', 'who gets named') rather than a crisp verb+resource, but an agent can still grasp the output. It also distinguishes itself from the sibling audit_site, which helps selection.

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 routes the agent: 'Use audit_site for anything that needs an answer now,' giving a clear condition that selects the alternative. It also explains the invocation pattern (call again with the same domain to collect the result). No hard exclusions beyond the timing tradeoff, but the routing guidance is concrete.

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