recognize_video

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

Beyond the annotations, it discloses important operational behavior: automatic temporary OSS direct upload for files over 14MB (1GB cap, no quality compression), base64 for small files, support for non-browser-playable containers such as mkv/avi, and server-side decoding/frame extraction. These are genuine behavioral traits that affect invocation success, and they do not contradict the annotation.

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 two sentences: the first states the purpose, and the second packs the key constraints into a compact list without filler. Every sentence earns its place and the most selection-relevant information is front-loaded.

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 a full schema, an output schema, and annotations present, the description covers the remaining invocation-relevant facts: accepted sources, size threshold, transfer method, and container compatibility. It could have explicitly routed an agent away from sibling tools, but the verb and resource plus the default task make the use case clear enough.

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?

The input schema already documents all four parameters with descriptions, defaults, and valid ranges (e.g., fps 0.1-10 default 2.0, mode options, task default, video path/URL). The description adds no per-parameter meaning beyond that, so the baseline of 3 applies given 100% schema coverage.

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 opening phrase '识别本地视频或视频 URL' names a specific verb (recognize) and resource (local video or video URL), which distinguishes it from recognize_image/recognize_audio and from generate_video tools. The additional details about decoding and frame extraction reinforce that this is an analysis tool, not a generation tool.

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 gives clear context for when the tool applies: it accepts local absolute paths or http(s) URLs and explains concrete file-size routing (>14MB via temporary OSS, smaller files via base64). It does not explicitly name alternatives or state when not to use it, so it stops short of full exclusions.

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