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

With readOnly/idempotent already declared in annotations, the description adds the state-dependent behavior an agent cannot get from the schema: ready:false on unfinished jobs, a failure reason on failed jobs, found:false on unknown ids, and the auth requirement of reusing the same _apiKey. This is precisely the non-obvious behavioral context that annotations do not cover.

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?

Front-loaded with the successful outcome, then the non-success branches, then auth — a sensible order with no filler. Slightly dense in the middle ("it does NOT return an empty result: it returns ready:false...") but every sentence carries distinct 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?

Given an output schema exists and annotations cover the safety profile, the description still fills the remaining gap by covering all outcome branches (success, not-ready, failure, unknown id) and the auth requirement. Nothing an agent needs to invoke and interpret this tool is missing.

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 both parameters are documented in the schema, including the job_id provenance from cds_submit_request and the PAT instructions for _apiKey. The description's sentence about the _apiKey largely restates the schema's "the one that submitted the job", so it adds little beyond the baseline.

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 ("Collect the output of a Copernicus Climate Data Store retrieval job") and enumerates the concrete return artifacts (href, file type, size, expiry). An agent can distinguish it immediately from cds_submit_request and cds_job_status, which the description implicitly contrasts.

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 routes the agent: when the job is not finished it tells you to poll cds_job_status, so the boundary between this tool and its sibling is named rather than inferred. It also implicitly defines this as the post-completion retrieval step, giving clear when-to-use guidance.

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