Build a GPT Image 2 prompt brief

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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive behavior, so the description only needs to add beyond them. It adds the critical behavioral fact that the tool does not generate an image, and characterizes the output as deterministic with constraints and revision moves. This is useful context beyond the structured fields.

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 two sentences, with the core action and output in the first sentence and a key limitation in the second. No filler or restatement of the title.

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?

The description neither explains the optional parameters nor describes the structure of the resulting brief, and there is no output schema to fill that gap. The phrase 'constraints and revision moves' hints at content but not at format or behavior. For a 6-parameter tool with one required field, more detail is needed for an agent to invoke it 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?

Schema coverage is 0%, so the description carries the full burden, yet it only vaguely references the input as a 'rough image idea' (aligning with the required 'idea' parameter). It says nothing about the meaning, usage, or effect of style, useCase, exactText, aspectRatio, or referenceConstraints. This leaves most parameters semantically opaque.

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 states a specific verb and resource: 'Turn a rough image idea into a structured, deterministic GPT Image 2 brief with constraints and revision moves.' It also explicitly distinguishes itself from image generation with 'This does not generate an image.' This clearly separates it from sibling retrieval tools like search_prompts and get_prompt.

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 the use case: when you have a rough image idea and need a structured brief. It does not, however, name any alternatives or state conditions for using search_prompts, get_prompt, or list_categories instead. The only exclusion is negative ('does not generate an image'), which is not enough to fully route an agent among siblings.

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