understand_video

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

No annotations exist, so the description carries full burden. It discloses supported formats (MP4, MOV, AVI, WMV), size limits (300MB URL, 50MB Base64), frame rate range (0.1-10, default 2), and effect ('越高时序越精细'). However, it does not mention potential latency, authorization needs, or failure modes.

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 well-structured with a short intro, usage guidance, parameter list, return info, and format/size notes. It is concise but contains necessary details; minor redundancy (e.g., 'Args:' and 'Returns:') could be trimmed.

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?

With 9 parameters, 1 required, and no enums, the description covers input semantics, output (MIMO model result), supported formats, and size limits. An output schema exists but is not shown; description helps complete the picture. Missing error handling or edge cases, but overall sufficient for a video understanding tool.

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 fully compensate. It explains all 9 parameters: prompt, video_url/path, video_urls/paths, fps (with default and range), media_resolution, system_prompt, and max_tokens (with defaults and max). This adds complete meaning beyond the schema.

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 explicitly states the tool uses a MIMO multimodal model to understand video, with examples like describing, summarizing, and identifying actions. It differentiates from sibling tools (understand_audio, understand_image) by being video-specific, achieving a clear verb+resource distinction.

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 explicit guidance: '何时使用' (when to use) for video content analysis, and '不要用于' (do not use) for metadata or source code. This clearly directs the agent when to select this tool versus alternatives.

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