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

Without annotations, the description clearly discloses the asynchronous nature (returns immediately with jobId, keywords not yet created), the cost (50c and AI spend), and the failure condition (if a run is in progress). This goes beyond what annotations would provide, giving critical behavioral transparency.

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, front-loaded with the most important info (async and cost), no filler. Each sentence adds essential usage information, making it efficient and scannable.

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 start-operation with no output schema, the description covers all necessary aspects: how to call, what to expect (jobId), what to do next (poll), and the limitations. Complete given the tool's simplicity.

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?

Even though the schema provides 100% coverage, the description adds value: it clarifies the 'brief' parameter's need for client context, reinforces the projectId format and warns against using slug or display name, and gives a starting point for targetCount (200). This enhances the schema information.

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 clearly states the tool's purpose: starting an asynchronous keyword-research run that mines keywords into pending rows. It uses specific verbs ('starts', 'mines', 'qualifies') and a definite resource ('keyword-research run'), distinguishing it from siblings like seo.audit.start and seo.content.generate.

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?

Explicit usage guidance is provided: call it once, poll seo.job.status until completed, and it fails if a run is already in progress. It also mentions cost implications, encouraging minimal calls. This clearly signals when to use and when not to use, and points to the polling alternative.

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