ocr_image

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states only 'OCR image recognition' and says nothing about whether the operation is read-only, what output format the OCR returns, whether network authentication is needed, or what happens on failure. This is a significant gap for an OCR tool.

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 extremely terse ('OCR image recognition') to the point of under-specification. It is a fragment that mostly repeats the tool name, and it does not front-load any useful operational detail such as 'Extract text from an image provided as a path or base64.'

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 one-parameter tool, the schema is sufficient to invoke the call, but the description never mentions the kind of result the OCR produces, whether it returns extracted text, a confidence score, or a structured result. Without an output schema and without a richer description, an agent cannot fully anticipate the tool outcome.

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% for the single 'image' parameter, which already specifies 'Image path or base64'. The description adds no extra semantic detail about parameter constraints, accepted formats, or how the image value should be structured, so the schema carries the load and the description provides no additional 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?

'OCR image recognition' states the tool's general purpose (performing OCR on an image), which is more specific than a pure tautology. However, it does not clearly express the action as 'extract text from an image' and offers no differentiation from the many sibling tools; it relies heavily on the tool name itself.

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?

There is no guidance on when to use this tool rather than alternatives such as get_image or send_msg. The description provides no context about prerequisites, preferred input sources, or conditions for use, leaving the agent to infer everything from the function name and schema.

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