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

Annotations already include readOnlyHint=false, idempotentHint=false, but the description adds critical context: it is ASYNCHRONOUS, returns a jobId, records findings, and costs 30c per call. It also explicitly limits scope to reporting only, which is beyond the annotations and informs the agent's expectations.

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 sentences with no redundancy. The first sentence front-loads the action and scope, the second gives the async pattern and follow-up step, and the third clarifies reporting-only and cost. Every sentence earns its place.

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 an async tool with an output schema, the description covers what it does, the defect types it finds, the async pattern and polling target, cost, and non-fixing behavior. Nothing essential is missing for correct invocation.

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 projectId parameter description is already extremely detailed (explaining what it is, how to get it, and that it's not a slug or name). The tool description adds no parameter-specific information, so a baseline of 3 is appropriate since schema does the heavy lifting.

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 (scans all generated pages) and resource (all generated pages), listing concrete defect types (broken text, unfilled placeholders, truncated copy, missing images). Clearly distinguishes from siblings like seo_content_generate and seo_publish by focusing on auditing and explicitly stating it only reports problems.

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?

Explicitly instructs to poll seo_job_status after receiving a jobId, giving a clear follow-up pattern. Clarifies that it does not fix issues, so the agent knows not to expect repairs. Does not explicitly state when to avoid using it or compare to alternative audit tools, but the async usage pattern is well defined.

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