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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-derivable behavior: the call is asynchronous, returns immediately with a job id, and that id is polled at cds.climate.copernicus.eu. That said, it never mentions rate limits, license acceptance per dataset, or what a job failure looks like.

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, each carrying a distinct load: what it does, what credential is required, and the async/polling contract plus the sibling handoff. Purpose is front-loaded and nothing is repeated from the schema.

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?

With no output schema, the description carries the return-value burden and does so ('job id and status'), and it explains the async completion path so the agent isn't left waiting on results. Combined with 100% schema coverage for the three required params, nothing needed to invoke or follow up on the call 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 description coverage is 100%, so the baseline is 3; the description still adds meaning by telling the agent where valid values for the nested 'inputs' object come from ('learn the accepted inputs' via cds_collection) rather than guessing at keys like variable/year/month. It does not add format details for inputs beyond that routing hint.

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 ('Submit a data-retrieval job to the Copernicus Climate Data Store') plus what comes back (job id and status). It is clearly distinguishable from the sibling cds_collection, which it explicitly names as the prerequisite step rather than a duplicate.

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?

Gives the ordering against the alternative ('Use cds_collection first to learn the accepted inputs') and the prerequisite for calling it at all (a BYO CDS Personal Access Token passed as _apiKey). It also sets the expectation that this is the submit step of a two-step async workflow, so the agent knows not to expect results here.

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