视觉解读

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

Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds useful behavioral context beyond that: it promises "不推测或脑补" (no hallucination) and discloses the automatic resizing behavior before sending to the VLM via max_dimension. This gives agents a realistic expectation of the tool's behavior.

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 reasonably front-loaded with the core purpose and remains compact. The parameter list and return-value note are helpful, though the opening sentences slightly overlap in meaning ("详细、真实地解读" vs. "忠实描述"). It is still efficient and free of irrelevant 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 read-only image-description tool, the description, combined with fully documented input parameters, strong annotations, and an output schema, covers everything an agent needs to invoke it correctly. It includes accepted input forms, detail-level options, resize behavior, and the nature of the returned description.

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 covers 100% of parameters with detailed descriptions, including accepted URL/path formats, enum values, defaults, and constraints. The description mostly restates this information, adding minimal new meaning, so the baseline score of 3 is appropriate.

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 opens with a specific action—"详细、真实地解读图片中的内容"—and clarifies the exact scope: describe all visible content without speculation. This clearly distinguishes it from siblings like vision_qa, vision_detect, and vision_ocr, which answer questions, detect objects, or extract text.

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 implies when to use the tool—whenever a faithful, comprehensive image description is needed—but it does not explicitly state when to prefer alternatives or mention exclusions. There is no direct routing to vision_qa, vision_detect, or vision_ocr, so the guidance is inferred rather than explicit.

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