understand_screen

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It describes the tool as returning structured analysis but does not confirm it is non-destructive (read-only), does not mention if screen capture is required, or disclose any side effects. The implied read behavior is not explicit.

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 (two short paragraphs) and front-loaded with the key analogy and output summary. Every sentence adds value, though the 'Returns' list could be slightly tighter.

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 simple parameter structure (one optional param) and existence of an output schema, the description adequately covers the basic inputs and outputs. However, it lacks error handling details, prerequisites (e.g., screen access permissions), and edge cases like empty screen or OCR failure.

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 coverage is 0% (no descriptions in schema), but the description explains the 'prompt' parameter's purpose and provides concrete examples ('explain this dashboard'), adding meaningful interpretation beyond the schema's default value.

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 'understand what's on screen' with a vivid analogy ('Google Lens for your desktop'), specifies output includes app, content, and insights, and distinguishes from siblings like 'capture_screen' (capture only) and 'read_screen_text' (text extraction). The optional prompt for focused analysis adds further clarity.

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 gives examples of when to use a custom prompt ('what error is this?') but does not explicitly differentiate from siblings such as 'analyze_image' or 'read_screen_text', nor does it state when not to use this tool. Usage context is implied but not clearly bounded.

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