Edit an image

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the agent knows this is a non-idempotent external write. The description adds nothing beyond that: it does not disclose that requests may be queued for slow models, that a job_id may be returned instead of an image, or that 'route' controls a privacy trade-off. The only extra content is accepted image input forms, which the schema's 'image' description already states verbatim.

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 short sentences, front-loaded with the action and followed by the input constraint; nothing is padded. The second sentence largely restates the schema's 'image' description, which is the main wasted content.

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 12-parameter, paid, potentially queued image-editing call with no output schema, the description omits the async/job_id path, cost and routing implications, and half the parameters. An agent could call it, but cannot predict latency, spend, or what a queued response looks like from this text alone.

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 50% across 12 parameters, with six (format, quality, safe_mode, resolution, aspect_ratio, prompt) undocumented. The description lists example imageEdit model ids, which adds a little meaning to 'model' beyond the schema's default-plus-pointer, but it says nothing about the undocumented knobs or about mode/wait_seconds queue behavior, so it only partially compensates for the coverage gap.

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 names a specific verb and resource ('Transform one image from a prompt') and gives concrete model examples (qwen-image-2-edit, nano-banana-2-edit, gpt-image-2-edit) that identify the model class in play. The phrase 'one image' implicitly separates it from carpe_image_multi_edit, but no sibling is named explicitly, so an agent must infer the boundary rather than read it.

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?

There is no statement of when to choose this over carpe_image_generate, carpe_image_multi_edit, or carpe_image_upscale, and no prerequisites or exclusions. The only routing hint is the word 'one', which is inference, not guidance.

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