generate_video

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

The description adds one genuinely useful behavioral fact beyond the annotations: results are downloaded to a local output directory and a path is returned. It does not contradict the annotations (readOnlyHint=false agrees with a generating/writing operation). However, it omits consequential behaviors such as the confirm-gate (must be true to actually invoke the paid API) and the asynchronous wait/return-task_id behavior, which the schema documents but the description does not surface.

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?

Two short sentences with zero waste: the core purpose is front-loaded ('文生视频'), and the second sentence states the output contract. Every word earns its place, and there is no repetition of schema content.

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 cost-incurring generation tool with no output schema, the description gives only a minimal output contract ('returns path') and does not flag the confirm-gate gotcha or cost implications in the main description — though the schema parameter descriptions do cover them. It is adequate for a basic call but not rich enough to fully prepare an agent for the tool's key behavioral decisions.

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 schema already documents all six parameters (prompt, tier, wait, confirm, duration, resolution) with informative detail, including model names per tier and the 480P auto-upgrade rule. The description adds no parameter-level meaning, so the baseline of 3 applies.

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 uses a specific verb-resource pair ('文生视频' — generate video from text) and immediately distinguishes this tool from the sibling generate_video_from_image. It also states the concrete output behavior (downloading the result locally and returning the path), leaving no ambiguity about what the tool accomplishes.

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 '文生视频' phrase implies the use case: call this when the input is text and the desired output is video, which implicitly differentiates it from image/video/audio recognition siblings and generate_video_from_image. However, no explicit when-to-use guidance, exclusions, or alternative tool names are given, so routing decisions are left to inference.

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