doubao_image_pro_generate

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

With no annotations provided, the description carries the full burden. It discloses that the tool automatically waits for results and returns a taskId on timeout, which can be checked via 'doubao_image_pro_result'. It also mentions that 'optimize_prompt' enables prompt optimization. This gives agents a clear picture of the async lifecycle. However, it does not mention any rate limits, authentication requirements, or potential side effects (e.g., cost), but for a generation tool this is acceptable.

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 concise (3 sentences) and front-loads the core purpose. It uses a semi-bulleted structure to explain parameters. Every sentence adds information, though the parameter explanation could be more formally organized. No superfluous text.

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 has 9 parameters and an output schema exists, the description covers the async behavior and the most important parameters (size, image, optimize_prompt). However, it neglects important parameters like prompt (the only required one!), watermark, output_format, and response_format. The output schema is not referenced, but since it exists, the description doesn't need to detail return values. The description is adequate for a quick understanding but not fully complete for complex usage.

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 0%, so the description must compensate. It explains 'size' (supports '1K'/'2K' or pixel values), 'image' (URL/Base64, single or list), and 'optimize_prompt' (but confusingly mentions 'standard/fast' which align with 'optimize_mode' in the schema, not the boolean 'optimize_prompt'). This leaves 6 out of 9 parameters (prompt, watermark, optimize_mode, output_format, response_format, timeout_seconds) unexplained. The description adds value for key parameters but has an ambiguity and incomplete coverage.

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 '豆包 Seedream 5.0 Pro 图片生成' (image generation) and '提交后自动等待结果' (automatically waits for results). It identifies the specific model version (Seedream 5.0 Pro), which helps distinguish it from siblings like 'doubao_image_lite_generate'. However, it does not explicitly contrast with other generation tools (e.g., gpt_image_generate), leaving some ambiguity about when to choose this tool.

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 provides no guidance on when to use this tool versus sibling tools like 'doubao_image_lite_generate' or 'gpt_image_generate'. It only explains internal behavior (timeout handling and async retrieval) but does not compare capabilities, cost, or quality. The agent is left to infer context from the tool name alone.

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