doubao_video_generate

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

Annotations are absent, so the description carries full responsibility for behavioral disclosure. It clearly states the tool submits a generation job, automatically waits for the result, and on timeout returns a taskId for later retrieval. This covers the key behavioral trait (async behavior with fallback). It does not mention rate limits, permissions, or whether the operation is destructive, but for a generation tool, the mutation is expected and the description adequately explains the wait-timeout pattern.

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 compact and front-loaded: the first line gives the core purpose. Parameter details are listed concisely. It could be improved by grouping optional parameters mentioned vs not mentioned, but overall it uses few words effectively.

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 complex tool with 10 parameters and an output schema (not inspected), the description covers the most important input parameter (content) well and explains the timeout behavior. But it misses many optional parameters and provides no guidance on output format (though the output schema exists). The tool has obvious siblings (doubao_video_result) and the description acknowledges that relationship. Overall, it's adequate but leaves optimization and edge-case handling to the agent.

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%, meaning the description must explain all parameters. The description covers 'content' (required, with detailed format examples), 'resolution', 'ratio', and 'duration' with valid values. It also mentions the special duration value -1 for intelligent duration. However, it omits explanation for 'seed', 'model', 'watermark', 'generate_audio', 'timeout_seconds', and 'return_last_frame', which are left entirely to the schema (which has no descriptions). Given the low coverage, this is a significant gap, but the most critical parameter (content) is well-covered.

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 tool is for '豆包 Seedance 2.0 视频生成' (video generation) and that submission automatically waits for the result. It distinguishes from sibling result-fetching tools like 'doubao_video_result' and other image generation tools (gpt_image, doubao_image). However, it lacks an explicit verb like 'create' or 'generate' in the first sentence, slightly reducing clarity.

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 explicit guidance on when to use this tool vs alternatives. It only mentions that 'doubao_video_result' can be used to check results on timeout, but doesn't explain when to prefer this over other generation tools (e.g., doubao_image_pro_generate) or how to choose between them. Missing context like prerequisites (e.g., need for reference images/videos) or typical use cases.

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