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

The annotations already declare non-read-only, non-idempotent, non-destructive, and open-world behavior. The description adds important context that the operation is billable and that it returns a job id, but it does not explain payload requirements, permissions, or rate limits.

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?

Two short sentences with the core action front-loaded and no wasted wording. The job id / get_job handoff is included efficiently.

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?

The output schema covers return values and the annotations cover safety behavior, but the required payload object is undocumented in both schema and description. For a tool that accepts arbitrary operation-specific payloads, this leaves a critical correctness gap.

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 0%, so the description must compensate. It gives useful example values for the operation parameter (fetch, batch_fetch, extract, crawl, research), but the required nested payload object is left completely unexplained despite being central to correct invocation.

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: run a billable operation as a background job, returning a job id. It clearly differentiates itself from get_job by naming the follow-up tool, though the enumerated crawl operation overlaps with the sibling start_crawl.

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 implies use for asynchronous/background work by saying it returns a job id for get_job, but it does not explicitly say when to use this tool versus synchronous siblings like fetch_url, extract_url, or start_crawl.

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