ocr_screen

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

No annotations are provided, so the description carries the behavioral burden. It usefully discloses the return shape (lines plus per-item centers for clicking) and the optional crop, and 'Read' implies a non-destructive operation. But it leaves scan_focus behavior unexplained and does not mention permission requirements or performance characteristics (OCR latency), which are material for an agent deciding whether to call it.

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?

Three sentences with zero waste: purpose is front-loaded, usage guidance follows, and behavior plus parameter semantics are packed into one efficient sentence. Every clause adds value.

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?

With an output schema present, return-value detail is already covered, and the description's mention of 'lines plus per-item centers' aligns with it. The main gaps are the unexplained scan_focus parameter and lack of explicit differentiation from window_capture_ocr among a large sibling list — both are things an agent needs 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 0%, so the description must compensate. It fully explains 'region' (format 'x,y,w,h' and optional crop semantics), but scan_focus is entirely undocumented in both the schema and the description — the agent cannot know what focusing behavior it toggles. With half the parameters unexplained, a 2 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?

Description states a specific verb+resource ('Read the screen as text with coordinates (OCR)') and differentiates from siblings: 'best for menus, dialogs, editors, chat — anything text-heavy' distinguishes it from screenshot (visual capture) and the sibling window_capture_ocr (window-scoped OCR). An agent can tell what this does without opening the schema.

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?

Provides clear when-to-use context ('text-heavy' interfaces such as menus, dialogs, editors, chat). However, it does not name the alternative window_capture_ocr or state when to prefer that sibling over whole-screen OCR, so exclusions are only implied, not explicit.

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