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

While annotations already declare readOnlyHint=true and idempotentHint=true, the description adds valuable context beyond annotations: it explains that signed output URLs can be recovered or refreshed, and that the lookup is read-only. This provides behavioral detail about URL refresh capability that is not present in the annotations, enhancing transparency.

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?

The description is concise and front-loaded: the first sentence states the main purpose, the second provides usage instructions, and the third adds a caution. Every sentence adds value, with no redundant or filler content. The structure is efficient and easy to parse.

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 simple tool with two parameters and an output schema, the description is complete. It covers what the tool does, how to use it, and important behavioral context (read-only, URL refresh). The output schema handles return value details, so the description does not need to explain them. It is fully sufficient for an agent to invoke the tool correctly.

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?

The schema has 100% coverage of parameters, with request_id described as 'Inference request id returned by create_inference.' The description reinforces this relationship but does not add additional semantic depth beyond what the schema already provides. Given the high schema coverage, a score of 3 is appropriate.

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?

The description clearly states the tool's function: 'Retrieve retained outputs for a synchronous generation.' This uses a specific verb ('retrieve') and resource ('outputs'), and distinguishes it from sibling tools like get_inference_job, which presumably retrieves job status. The purpose is unambiguous and differentiated.

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?

The description provides explicit usage context: use the request_id returned by create_inference, and it explicitly warns against repeating a paid create_inference call when URLs are missing. This gives clear when-to-use and when-not-to-use guidance, effectively differentiating from the create_inference sibling tool.

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