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

Annotations already cover read-only/idempotent safety, but the description adds two things the annotations cannot: failed generations have had their credits refunded, and partial completion is expected so re-polling is the correct behavior. It does not mention any rate limits or caps on repeated polling, which keeps it just below a 5.

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?

Opens with the resource and its provenance, then enumerates return values, then gives usage instructions — well front-loaded. The single long opening sentence is dense with list items but every clause carries information the agent needs.

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 full burden of describing the response and does so completely: status enum, mediaId, URL, and error text on failure. Combined with the polling instruction, an agent can call and interpret results without guessing.

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%, so the baseline is 3, but the description adds meaning to waitSeconds that the schema does not — it frames it as a poll-and-call-again loop rather than a one-shot blocking call. jobIds and projectId are left to the schema, which is adequate given its provenance hints.

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 exactly what is returned for jobs created by run_generations: status values (queued, running, succeeded, failed, canceled), each new image's mediaId and URL, and the error text for failures. This separates it cleanly from run_generations (which starts them) and get_import_job (a different job type).

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 explicit operational guidance: pass waitSeconds to block, 'call again with the jobs still running' to poll, and inspect mediaId with view_media before declaring success. It also tells the agent to report each result or failure to the user, so the follow-up action is unambiguous.

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