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

With no annotations, the description carries the full burden: it usefully discloses the return shape (status, progress, asset links when done) and the API-key scoping constraint. It omits terminal-state semantics, whether an unknown or expired id errors, and whether reads are side-effect free.

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 short sentences, front-loaded with the action, then the payoff, then the scoping caveat. Nothing is padded or repeated.

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 a single-parameter polling tool with no output schema, the description covers the verb, the required input's origin, the return fields, and auth scoping. Polling cadence and terminal/error states are the remaining gaps.

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 the schema already explains that job_id comes from an async generate tool, so the description adds almost nothing beyond 'by id'. Baseline 3 applies when the schema does the heavy lifting.

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 ('poll a background generation job by id') plus the return payload, which is enough to tell it apart from the generate_* siblings that create jobs. It stops short of naming those siblings explicitly as the creating counterpart.

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?

'Poll' implies repeated invocation while a job is in flight, and 'by id' ties it to the async generate tools, so usage is inferable. However, it gives no guidance on polling cadence, when to stop, or what to do with a failed/expired job id.

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