图片合规检测

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

With no annotations, the description carries the full burden. It discloses key behaviors: auto-upload for local files, credit deduction ('会扣积分'), and product line restrictions. This goes beyond schema and gives important operational context, though it does not describe the return format or error cases.

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 tightly written in three sentences, front-loading the core purpose first, then usage input methods, then exclusions and cost. No wasteful sentences or repetition.

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 description covers purpose, input methods, product restrictions, and cost, but lacks details on return values, error conditions, or how results are delivered (especially given no output schema). The existence of sibling get_check_result implies a separate retrieval step, but this is not mentioned, leaving the workflow incomplete.

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 coverage is 100%, but the description adds meaningful param semantics: clarifies image supports local path vs URL and auto-upload behavior, and explains productVertical limitation (short drama unsupported). This adds value beyond schema, which already provides descriptions for all parameters.

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 the tool detects image compliance risks across specific categories (广告违规, OCR文字, 涉政, 暴力, 色情, 侵权Logo). This specific verb+resource+scope distinguishes it from sibling tools like check_text and check_video, and the title (图片合规检测) aligns well.

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?

Provides clear usage context: supports local file paths (auto-upload) or public URLs, and explicitly states the short drama product line is unsupported ('短剧产品线没有图片检测'). However, it does not explicitly mention alternatives like check_text for text-only scenarios, so it lacks full when-not/alternative guidance.

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