Read Screen Text (OCR)

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

With no annotations, the description carries the full behavioral burden and does disclose several real traits: the token-cost profile (~10-100x fewer tokens than vision), the performance penalty of omitting region, and a security warning that OCR text is untrusted and may contain attacker-crafted prompt-injection content. It does not mention OS-level screen-recording permission requirements or failure behavior, which are the remaining gaps.

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 tight sentences: purpose and cost trade-off first, then the opt-in flag, then the security warning. No filler, nothing repeated, and the most decision-relevant information is 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?

No output schema exists, and the description does describe the return shape (recognized text, optionally per-line bounding boxes with confidence in display coordinates). Missing only secondary operational details such as permission prerequisites and what happens on an empty/failed OCR pass.

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%, so the baseline is 3. The description adds meaning beyond the schema by framing the text-only default as a token-saving choice and by stating that line boxes are meant for 'follow-up region capture' (linking to screenshot_region), plus the maxLines default is documented in the schema itself.

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?

States a concrete verb+resource (run OCR on the screen or a region and return recognized text) and explicitly contrasts itself with the `screenshot` sibling on cost, so an agent can pick between them without opening either 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?

Gives a clear selection rule ('cheaper than screenshot when you only need text') and explains when to enable includeLineBoxes (follow-up region capture). It never mentions the closely related `find_text_on_screen` sibling, which an agent might otherwise confuse with a text search on screen, so it stops short of full alternative coverage.

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