视频合规检测

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses billing (1 credit/second), long processing times for long videos, auto-upload from local file paths, support for direct links, and optional drift detection via textCheckId. The param description also notes automatic deduction for under-reported duration, adding to the transparency.

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 three concise sentences that front-load the primary purpose, then cover input methods, billing, wait times, and an optional advanced feature. Every sentence adds unique value without repetition or filler.

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 complex tool with 8 parameters and no output schema, the description covers key usage context: main function, input methods, billing, wait behavior, and optional drift detection. It mentions the return format as 'risk details with timestamps' but does not fully describe the response structure or timeout handling (though timeout is in the waitSeconds param). Overall, it is quite complete but could add a bit more about the output shape.

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 schema covers 100% of parameters with detailed descriptions, so the baseline is 3. The main description adds extra context beyond the schema by explaining the billing relationship with durationSeconds and the cross-check purpose of textCheckId, linking it to check_text. This enriches the parametric understanding without redundancy.

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 explicitly states that the tool detects compliance risks in video visuals, audio, and spoken script, and returns timestamped risk details. This clearly distinguishes it from sibling tools like check_text and check_image, which target different media types. The name 'check_video' and title '视频合规检测' reinforce the purpose.

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 conditions for using textCheckId (when the script was previously checked via check_text) and mentions billing and wait times to set expectations. However, it does not explicitly contrast with alternatives like check_image or specify when not to use the tool, though the media type distinction is evident from the tool names.

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