Extract Text from Screen (AI) [Pro]

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

The description discloses the behavioral trait of returning text in reading order (top to bottom, left to right), which is beyond the schema. Since no annotations are provided, this adds value by informing the agent of the output format. It does not contradict any annotations.

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 concise with three sentences, each adding value: first states what it does (pro and AI vision), second specifies output order, third gives use cases. No waste.

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 the single parameter and lack of output schema, the description adequately explains the tool's purpose and usage. However, it could mention returns plain text or format details for full completeness.

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 schema has 100% coverage for the single parameter 'device_id' with a clear description. The tool description does not add extra meaning to the parameter beyond the schema, so baseline 3 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?

The description clearly states the tool uses AI vision to extract visible text from the current screen, with a specific verb ('extracts') and resource ('current screen'). It distinguishes itself from siblings like 'take_screenshot' (image capture) and 'get_ui_elements' (accessibility tree) by noting it gets text not in the accessibility tree.

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 says it's useful for 'reading content, checking labels, or getting text that isn't in the accessibility tree,' providing clear use cases. However, it does not explicitly state when not to use it (e.g., if text is accessible via UI elements) or mention alternatives from the sibling list.

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