refine_image

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

With no annotations, the description carries the full burden. It discloses important behaviors: cost (0 credits), retry limit (5 per parent prompt ID), and that modifications are appended to the locked base prompt (implying additive changes). It doesn't mention output format or failure modes, but the core behavioral traits are covered.

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, no fluff. Every word adds useful info: cost, retries, and the append behavior. Well-structured and easy to scan.

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, 100% schema coverage, and no output schema, the description covers purpose, cost, retry limit, and prompt handling. It doesn't describe the response format, but for a refinement tool this may not be critical. The description is sufficiently complete for selection and basic invocation.

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. The description adds value by explaining that prompt_update is appended to the base prompt and that parent_prompt_id refers to the original generation, which clarifies the relationship between parameters and the tool's operation.

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 uses specific verbs ('Refine or modify') and a clear resource ('existing generated image'), distinguishing it from sibling tools like generate_image. It also mentions appending prompt modifications to the locked base prompt, which clarifies its unique function.

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 implies usage context: for modifying existing images with 0 credits and up to 5 free retries per parent prompt ID. It provides a strong reason to use this tool over generate_image, even if it doesn't explicitly state 'use when you want to edit an existing image rather than create a new one.'

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