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

With zero annotations, the description carries the full burden and does an excellent job: it flags ASYNCHRONOUS, states the financial cost (25c plus per-page), relies on project configuration, and discloses the state transition (GENERATED, not live). This goes well beyond what the schema conveys.

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?

The description is a single, dense sentence group that front-loads the critical flag (ASYNCHRONOUS) and then layers the prerequisite, side effect, and follow-up action without a single wasteful phrase. Each sentence carries necessary information.

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?

Although there is no output schema, the description explains exactly what is returned (jobId), how to proceed (poll seo.job.status), and what the result state is before publishing. Paired with 100% schema coverage, this is complete for an async tool with a single parameter.

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%, so the schema already documents projectId fully. The description adds no additional parameter meaning beyond reinforcing that it refers to the whole project and all pending rows, which is minor. Baseline 3 is appropriate.

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 ('starts'), resource ('content-generation queue'), and scope ('every PENDING row'), which clearly distinguishes it from sibling tools like seo.audit.start and seo.research.start. The status outcome ('GENERATED... NOT live') further pins down the purpose.

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 tells when to call it: after verifying readyToGenerate via seo.project.get. Also directs the subsequent flow by telling the agent to poll seo.job.status and to not treat generated pages as live until approved and published. No similar guidance is needed for siblings.

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