screen_ocr

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It mentions the tool is non-destructive (read operation) implicitly, but does not state safety, permissions, or rate limits. The description adds value by explaining the return format and usage, but lacks explicit behavioral traits.

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 two sentences: first establishes purpose and output, second provides actionable usage. No wasted words; highly concise and 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?

Given that the input schema covers all parameters with descriptions and there is no output schema, the description explains the return format and how to use it. It does not elaborate on corner cases or all parameters, but it is sufficient for a tool with five optional parameters where schema provides details.

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 coverage is 100%, so baseline is 3. The description does not add significant new meaning beyond the schema for individual parameters. It contextualizes the output coordinates for clicking, but that is not parameter-specific. Thus, it meets the baseline but does not exceed.

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 clearly states the tool performs OCR on the screen using Apple Vision and returns text elements with pixel coordinates. It also explains how to use the output with click_at, distinguishing it from siblings like find_text_on_screen which searches for specific 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 provides guidance on using the output coordinates with click_at. It implies when to use the tool (full screen or specific app) but does not explicitly state when not to use it or compare to alternatives like find_text_on_screen.

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