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

With no annotations provided, the description carries the full burden and does so thoroughly: it discloses asynchronous behavior, the cost, the return of a jobId, the polling mechanism, the scope ('all generated pages'), and the non-mutating 'reports only' behavior. This gives the agent an accurate operational model before calling.

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 pack essential operational details while staying readable. The ASYNCHRONOUS warning is front-loaded, followed by scope, cost, return type, polling instruction, and an important limitation. No sentences are wasted.

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 one-parameter async tool with no output schema and no annotations, the description covers everything needed to invoke and follow up correctly: what it scans, what it reports, what it costs, what it returns, and how to retrieve results. The absence of an output schema is mitigated by the explicit pointer to seo.job.status.

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 description coverage is 100%, and the schema itself already explains that projectId must be the exact cuid from seo.project.list rather than a slug or display name. The description adds little about the parameter, but the schema is strong enough that no additional compensation is needed.

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 behavior: scanning all generated pages for broken text, unfilled placeholders, truncated copy, and missing images, recording findings per page. It also distinguishes itself from any fix-oriented operation by explicitly stating that it only reports problems and does not fix them.

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?

The description clearly tells the agent this is asynchronous, should be followed by polling seo.job.status, and is for reporting rather than fixing. It also embeds a prerequisite in the parameter description: call seo.project.list first if no projectId is available. It does not name an alternative audit tool, but none is needed among the siblings.

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