Perceive Screen

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

No annotations are provided, so the description carries the full burden. It discloses that ids are single-use and go stale after any action, and explains the ocr modes including the 'auto' condition. These are genuine behavioral details beyond a simple 'captures screen' statement, but it omits permission requirements and return format.

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 compact—three sentences with no filler. The main function is front-loaded, followed by the critical staleness warning and the ocr parameter semantics. Every sentence serves a distinct 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?

A 5-parameter tool with no annotations and no output schema demands more context. The description explains the tool's purpose but fails to cover the meaning of most parameters and does not describe the return structure of the annotated screenshot or marks. This is a significant gap for correct invocation.

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 0%, so the description must compensate for all 5 parameters. It explains 'ocr' semantics (auto/always/never) but leaves lang, device, max_marks, and include_image completely unexplained, providing minimal help for an agent selecting parameter values.

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?

Description states a specific verb (Capture), resource (screen), and output (numbered marks plus annotated screenshot). It clearly differentiates from sibling tools like get_screenshot (plain screenshot) and get_ui_tree (tree only) by promising interactive som_ids for tappable/readable items.

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 doesn't explicitly name alternatives or when-not-to-use conditions. It implies usage when interactive elements with ids are needed, but lacks explicit comparison to get_screenshot or read_screen. The ocr explanation gives parameter guidance but not tool-selection guidance.

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