edit_image

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

With no annotations provided, the description carries full disclosure burden. It does mention it creates an asynchronous task and returns task id/status/output URLs, giving some sense of async behavior. However, it doesn't disclose rate limits, auth requirements, wait versus callback behavior, or what happens to the source image. Some context is added but not comprehensive.

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 a single efficient sentence conveying the core purpose and return shape. It's appropriately front-loaded and contains no filler. It could perhaps add a sentence on usage guidance, but as written it's compact and readable.

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?

This is a complex tool with 10 parameters and no output schema, but the description doesn't explain parameter interactions, async task semantics (wait/poll/callback options), or how results are retrieved. It mentions returning output URLs but doesn't connect to the async task model or the get_task sibling. Given the complexity and lack of output schema, more explanation is warranted.

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 80%, so the schema already documents most parameters. The description adds the overall behavioral context (returns task id/status) but doesn't elaborate on parameters beyond what the schema describes. With high schema coverage, baseline 3 is appropriate — description adds modest value but doesn't compensate for the 20% uncovered.

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 action (Create a Qwen Image task), the resource (RunAPI edit image), and the return payload (task id, status, output URLs). It distinguishes from siblings like text_to_image and remix_image which cover generation/remix rather than editing. However, it doesn't explicitly contrast with the sibling edit-related tools.

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?

No guidance on when to use this tool versus alternatives. It doesn't clarify how it differs from remix_image (which may also modify existing images), nor does it state prerequisites like needing an existing image URL. Usage context is only implied through the tool name and description.

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