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 the model used, self-call restriction, supported formats, and size limits. However, it omits potential costs, latency, or authentication requirements, but overall provides sufficient transparency for a read operation.

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?

Moderately long but well-structured with sections for general info, warning, usage, args, returns, and constraints. Every sentence adds value, no redundancy.

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 complexity (9 parameters, output schema exists), the description covers all parameters, return description, format support, size limits, and usage guidance. Output schema exists, so return details are sufficient. Comprehensive for the tool's purpose.

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 0% (no parameter descriptions in schema), so description carries full burden. It explains every parameter in detail (prompt, video_url, video_path, fps, resolution, etc.) with examples, default values, and ranges, adding substantial 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 clearly states the tool calls the MIMO multimodal model to understand video, with examples of tasks like describing, summarizing, and recognizing actions. It distinguishes from sibling tools (understand_audio, understand_image) by focusing on video.

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?

Explicitly states when to use (analyzing, describing, summarizing video content) and when not to use (reading metadata or source code, which should use other tools). Also includes a critical self-call warning for the integrated model.

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