Discover search keywords

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

Annotations cover the non-destructive, non-idempotent, open-world profile, and the description adds value beyond them: it discloses the asynchronous background-job nature, the need to poll get_job, and the subscription precondition. It stops short of describing job lifetime, rate limits, or expected runtime.

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 tight sentences: the action first, then the exclusion parameter, then the end-to-end workflow. Every sentence carries distinct information with no padding.

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 mutation tool with no output schema, the description correctly redirects to get_job for results and names the follow-up tool for committing results, which is the essential context. Minor gaps remain around the undocumented country/language parameters and job timing.

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 very low (14%), so the description must compensate. It explains input (seed can be a topic, product, or URL) and excludeQueries semantics ('leaves out ones already tracked'), but says nothing about country, language, or how organizationId/projectId scope the job.

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 and resource ('Start a background job that proposes search keywords for a project from a seed') and clarifies the seed forms (topic, product, URL). It is clearly separable from siblings discover_brands, discover_prompts, and create_tracked_queries.

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?

Lays out the full workflow: start the job, poll get_job for results, review with the user, then track with create_tracked_queries. It also names the preconditions (excludeQueries for already-tracked queries, active subscription requirement), leaving little to inference.

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