视觉OCR

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior. The description adds meaningful context beyond annotations: images are automatically resized before being sent to the VLM, controlled by max_dimension, and the output is a structured JSON with text_blocks and full_text. No contradiction with annotations exists.

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 compact and front-loaded with the core purpose. It then presents parameters clearly and gives a concise JSON output example. Every section earns its place with no filler 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 the required parameter, the optional parameter, preprocessing behavior, and the exact return shape. Combined with the safety profile from annotations and the presence of an output schema, an agent has everything needed to invoke this tool 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%, and the parameter notes in the description essentially restate what the schema already provides. No additional nuance or format detail is added for images or max_dimension, 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 states a clear verb and resource: extract all text from images, and enumerates content types such as titles, body, labels, and button text. This makes it unambiguous as an OCR tool and distinguishes it from sibling tools like vision_describe, vision_qa, and vision_detect.

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 use case is implied—use this when you need all visible text from an image—but it never explicitly contrasts it with vision_describe or vision_qa, nor states when not to use it. The agent must infer the routing from the tool name and general purpose.

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