视觉检测

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

Annotations already cover safety (readOnly, non-destructive, idempotent, openWorld). The description adds meaningful behavioral context beyond annotations: automatic resizing before sending to the VLM, the option to disable it via max_dimension=0, and normalized coordinate conventions for bounding boxes. No contradictions with annotations.

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 well-structured with an opening summary, parameter list, and return format example. It is somewhat longer than strictly necessary because some parameter details repeat the schema, but every section is readable and the core purpose 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 annotations covering safety, a 100%-covered schema, and an output schema present, the description still adds valuable context around normalization, scaling behavior, and detection semantics. The tool is fully specified for an agent to select and invoke correctly.

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 three parameters. The description adds useful examples for target descriptions and clarifies the URL vs local path behavior, but it largely duplicates schema information rather than introducing substantial new meaning.

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 states a specific verb ('检测'), a clear resource (images), and a well-defined outcome (normalized bounding boxes). The phrase '返回所有检测到的目标的位置信息' makes it distinct from sibling tools like vision_qa or vision_ocr, even without naming them.

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 intended usage is implied through the description and parameter guidance, and the tool's purpose is clear enough to infer when to call it. However, there is no explicit statement of when to choose this tool over vision_qa, vision_describe, or vision_ocr, and no exclusions are mentioned.

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