describe_video

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

No annotations are provided, so the description carries full burden. It discloses the upload to Gemini, conditional parameter interactions (prompt overrides persona/hint), internal token counting (thinking tokens count toward max_output_tokens), low_resolution speed tradeoffs, and return-value caveats (usage stats/truncation). This is very transparent.

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 front-loaded with the core purpose, then organized into Args and Returns sections. Though lengthy, every sentence adds value—format support, parameter semantics, conditional overrides, and token behavior—without redundancy. It is efficiently structured for a complex tool.

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?

The tool has no output schema, but the Returns section clearly describes the output. All parameter interactions, edge cases (e.g., 2048 token floor, thinking token consumption, environment variable), and behavioral notes (e.g., .gif not frame-sampled) are covered. The complexity is fully addressed; no gaps remain.

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%, but the description explains all 6 parameters in detail: path (absolute path recommendation), prompt (overrides defaults and ignores persona/hint), persona (appends to default prompt only when prompt absent), hint (injects background context into default template), low_resolution (token rate tradeoff), and max_output_tokens (default, floor, thinking token interaction). This fully compensates for the missing schema descriptions.

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 opens with a specific verb+resource: '把本地视频交给 Gemini 直传识别，返回按时间轴分段的详细内容描述（画面 + 音轨）'. It clearly states what the tool does (describes local videos via direct upload to Gemini) and distinguishes itself from the sibling 'describe_video_url' by emphasizing local file paths and direct upload.

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?

It provides clear context on when to use: for local video files with supported formats (mp4/mov/webm/avi/mkv) and .gif. However, it does not explicitly mention when not to use it or name alternatives like describe_video_url, so it falls short of a 5.

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