recover_generated_image

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

With no annotations provided, the description carries full responsibility for disclosing side effects. It clearly discloses that it decodes from the session log and writes to disk, and returns absolute paths. It does not mention failure modes or overwrite behavior, but the core behavior is transparent. This is strong given the absence of 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?

Three sentences pack in the action, rationale, and parameter details without redundancy. Each sentence adds value: the first states the core function, the second explains the need and output, the third defines parameters. This is concise and well-structured.

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?

Given the tool's moderate complexity and lack of output schema, the description provides sufficient context: it explains why the tool exists, what it returns, and how to pass results to reply/send_message. It doesn't address error handling or edge cases, but for a 2-parameter utility, it is nearly complete, hence a 4 rather than 3.

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 no descriptions (0% coverage), so the description must compensate. It does so effectively by explaining 'count (default 1)' and 'session_file (absolute rollout path; defaults to the newest session),' adding meaning beyond the plain types. It doesn't specify constraints like valid ranges, but the core semantics are covered.

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 primary action: 'Recover the most recently generated image(s)... and write them to disk.' It distinguishes itself from siblings by explaining the Codex inline preview limitation and that this tool decodes and saves the image, differentiating it from tools like latest_generated_images or reply.

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 explicitly explains when to use this tool: when Codex's image_gen shows an inline preview but doesn't write a file. It also notes the output is 'ready to pass to the files array of reply/send_message,' indicating a clear integration point. However, it doesn't explicitly mention alternatives or when not to use it, so it falls just short of a 5.

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