vision.ocr

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

With no annotations, the description carries the full burden and does reasonably well: it discloses lazy-loading of rapidocr_onnxruntime, an explicit error when the dependency is missing, offline/no-device-connection operation, and the screenshot fallback. It omits performance/rate characteristics, but the operational behaviors that matter for invocation are present.

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?

Dense and front-loaded with the core purpose, using semicolons to pack dependency, error, and default behaviors into one line. No wasted text, though the heavy parenthetical phrasing slightly compresses readability.

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 2-param tool with no output schema, the description covers purpose, dependency loading, error behavior, offline mode, and default input. It is incomplete on the region parameter and says nothing about the return format (recognized text structure), leaving real gaps.

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 path parameter is clarified (offline local image, defaults to screenshot when omitted), adding value beyond the schema. But the region parameter (array of integers, e.g. a crop box) is undocumented in both schema and description, leaving half the parameters without meaning at 50% coverage.

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 gives a specific verb+resource (OCR on a local image), and clarifies the default behavior when path is omitted (screenshot). It does not explicitly differentiate itself from vision-adjacent siblings like vision.vlm or vision.ask, which also extract information from images, so it stops short of full sibling disambiguation.

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?

Usage is implied: use it to OCR a local image, or a screenshot by default. The description notes offline mode requires no device connection, which hints at when this is preferable. However, there is no explicit when/when-not guidance or named alternative (e.g. use vision.vlm for semantic understanding instead of raw text).

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