analyze_video

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

No annotations are provided, so the description carries the full burden. It discloses useful behaviors: local videos are auto-compressed, fps affects temporal detail and token consumption. However, it does not explain the return format, whether the operation is read-only, or other behavioral aspects like potential latency or auth requirements. This is a moderate level of disclosure.

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 extremely concise and front-loaded: two sentences cover the purpose, supported input types, compression behavior, and fps guidance without any fluff. Every sentence earns its place.

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 tool with 6 parameters and no output schema, the description provides sufficient context: it explains what the tool does, what inputs are accepted, and key usage notes. It lacks an explicit description of the return value, but the purpose ('描述视频内容、按时间顺序总结') implies a textual summary, which is adequate given the schema's detailed parameter descriptions.

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 100%, so the baseline is 3. The description adds value beyond the schema by explaining the fps parameter's effect on detail and token usage, recommending the default, and noting that local videos are auto-compressed—details not in the schema. This enrichment justifies a score above baseline.

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 a specific verb and resource: '视频理解' (video understanding) and describes what it does: '让模型描述视频内容、按时间顺序总结' (let the model describe video content and summarize chronologically). This differentiates it from sibling tools like analyze_image and analyze_audio by its focus on video content understanding.

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 clear context for when to use the tool: for video understanding with support for local files, URLs, or base64, and includes guidance on fps (default 2, range 1-30, larger means finer detail but more tokens). It does not explicitly name alternatives or exclusions, but the context is clear enough for an agent to select it appropriately.

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