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

Annotations only declare it as a safe read; the description goes well beyond that with a 30-day retention limit, environment scoping, the failure payload shape (error.message, error.api_said, error.next_step), and the conditional include_body behavior gated on the environment's 'Save prompts and answers' setting. These are behaviors an agent cannot infer from the schema or 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?

A single dense paragraph, but it is front-loaded with identity and lookup, then return fields, then error handling, then the include_body caveat. Nearly every clause carries operational information; only the long return-field enumeration is slightly list-like for prose.

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 return values and does so (status, outcome, timings, tokens, cost, tags, error fields, body). Combined with not-found causes and the two actionable failure modes, an agent has everything needed to call and interpret this tool.

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 baseline is 3, but the description adds real meaning: the accepted id formats (header, list id, chatcmpl- prefix) and that include_body may return body.saved=false rather than body content. That conditional semantics is not captured in the schema's 'Also return the saved prompt and answer' line.

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 ('Get one call to a model by its request id') and immediately distinguishes it from the sibling list_requests by noting the id can come from that listing. Field names returned are enumerated, so an agent knows exactly what it gets.

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 concrete routing cues: id can come from the X-Request-Id header, from list_requests, or as a chatcmpl-<id>. It also prescribes follow-up actions on failure ('do what next_step says, then retry') and on finish_reason 'length' ('raise max_tokens'). It does not explicitly say when to prefer list_requests or get_job instead, so it stops short of full alternatives guidance.

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