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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds value beyond that: it maps the status lifecycle (queued|running|completed|failed), explains that Assets/OutputText only appear when done, and notes the operation is free – all context an agent cannot get from annotations.

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 sentences, front-loaded with the core action and its return shape, followed by the polling guidance. Every clause earns its place with no filler.

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 read with no output schema, the description covers the essential return shape and the polling pattern well. It could note pagination/expiry of CDN URLs or rate limits, but nothing critical for correct invocation 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 the single generation_id parameter is fully documented in the schema, including its origin ('Id returned by a generate_* tool'). The description adds little parameter-level detail beyond restating 'by id', so 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 and resource ('Read a generation by id') and enumerates the fields it returns (status with full enum, Assets CDN URLs, OutputText, error). This distinguishes it from the many sibling get_* tools by naming exactly the generation artifact and its lifecycle states.

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 tells the agent when to use it for polling ('Poll it for generations that returned queued/running'), which is the key non-obvious usage pattern given the generate_* siblings that produce the ids. No exclusions are needed because the scope is already narrow.

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