ocr_screen

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

With no annotations, the description carries full weight. It discloses the underlying engine (RapidOCR), the output shape (JSON array of {text, conf, x, y, w, h}), and the sorting order. It does not explicitly state side effects or permissions, but the read-only nature is implied sufficiently.

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 three concise sentences: action, use-case, and output format. Each sentence delivers unique information without redundancy, front-loading the core purpose.

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?

The description thoroughly covers the tool's purpose, usage context, and output format. However, it omits any explanation of the 'device' parameter, which is the sole input and is also undocumented in the schema. Despite having an output schema, the description redundantly details the return structure, which is acceptable but not necessary.

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 defines a required 'device' string with no description, and the description never mentions this parameter. With 0% schema coverage, the description should explain how to populate 'device', but it is completely absent, leaving the agent guessing.

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 opens with a specific verb and resource: 'OCR the entire device screen using RapidOCR.' It clarifies scope ('entire device screen') and distinguishes from siblings like ocr_region and get_elements by explicitly contrasting with get_elements in the usage sentence.

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 second sentence explicitly states when to use this tool—when UI elements are rendered as images/canvas where get_elements() returns no text—and provides concrete examples (dashboards, games, WebViews). This is a clear directive that also implies the alternative.

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