Edit Image

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose the return shape — JPEG previews per result plus URL and id of the full-resolution PNG — which is information an agent cannot get elsewhere since there is no output schema. It omits cost, latency expectations (except what quality hints at in the schema), and whether results are retained or how long the returned URLs live.

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 short sentences, front-loaded with the capability, then the single-image case, the multi-image case, and the return format. Every sentence carries distinct information and the example phrasings are short enough to be read rather than skipped.

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 ten-parameter mutation tool with no annotations and no output schema, the description covers the essentials: what it does, how to prompt for both modes, and what comes back. The gaps — no explicit routing to generate_image, no cost or timing, no mention of optional knobs like boxes or quality — are real but secondary given how much the 100%-covered schema carries.

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 description coverage is 100%, so the schema documents all ten parameters including boxes, count, quality, and enhance_prompt, making 3 the baseline. The description reinforces prompt semantics with worked examples ('the woman from the first image standing in the forest from the second image'), which adds real value beyond the terse schema text, but it never touches boxes, quality, or count.

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 ('Edit an image, or combine several reference images') plus the backing model, and the one-vs-many framing immediately conveys the two modes. It stops short of explicitly contrasting with generate_image, which is the closest sibling and the main source of confusion for an agent choosing between creating and editing.

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 gives genuinely useful in-tool guidance: how to phrase a single-image edit and how to reference multiple images by order, with concrete example phrasings. It says nothing about when to pick this over generate_image, upscale_image, or remove_background, and no exclusions or prerequisites (e.g., that images are required, source of those images) are stated.

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