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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely useful behavior beyond that: this is a polling endpoint whose useful payload (the preview) only appears once the job is completed, and re-uploading is not the recovery path.

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 compact sentences, front-loaded with the action and result. One sentence is marred by the truncated 'job cmup… IDs' text, which reads as a defect rather than intentional brevity.

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 job-polling tool with no output schema, the description covers the important things: when to call it, that results arrive only on completion, and the re-upload pitfall. It stops short of stating terminal failure states or polling cadence, which would make it fully self-sufficient.

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?

Only one parameter and the schema documents it at 100% ('Job id from anonymize_document'). The description reinforces the source of the id but adds no format or syntax detail beyond what the schema already says, so the baseline 3 applies.

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+resource ('Check an anonymize job') and adds the key output behavior ('return the preview when it is completed'), which distinguishes it from anonymize_document. The stray truncated fragment 'job cmup… IDs' slightly blurs an otherwise clear statement.

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 trigger conditions: use after anonymize_document returns running/queued, or to recover job IDs, plus a clear prohibition ('Do not re-upload the file'). It names the sibling and the state that selects this tool, though the truncated 'recover job cmup… IDs' clause is partially unusable.

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