Find Text on Screen

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

With no annotations, the description carries the full burden and does well: it discloses the return format, the coordinate system (display-coordinates, not image pixels), and a security caveat about prompt-injection content in OCR output — a real, non-obvious behavioral risk. It omits OCR latency/cost and whether the call is side-effect-free, which is why it falls short of 5.

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, front-loaded with the core action, then chaining guidance, then the warning — each sentence earns its place with no repetition of schema content.

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?

There is no output schema, but the description compensates by describing the returned 'matching lines with display-coordinate bounding boxes' and how to consume them, and it flags the untrusted-content risk. Coverage is solid for a read-only lookup tool; only cost/permission behavior is left implicit.

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 every parameter (query, region, displayId, maxMatches, caseSensitive) is already documented including defaults and bounds. The description adds no parameter-level meaning beyond what the schema states, so the baseline 3 applies.

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 specific verb (search) and resource (screen region) with the mechanism (OCR) and return shape (matching lines with bounding boxes). It also distinguishes itself from siblings by naming the downstream consumer, `screenshot_region`, which no screenshot/read_screen_text tool would do.

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 three concrete example intents ('find the error message', 'where is the submit button') and an explicit follow-up action. It stops short of stating when NOT to use it versus `read_screen_text` or `screenshot`, but the triggering context is clear.

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