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

With no annotations provided, the description carries the behavioral transparency burden. It gives one valuable behavioral detail: the coordinate space is physical pixels from device_page_source, eliminating scaling guesswork. However, it doesn't disclose what happens on failure (e.g., swipe off-screen), whether there are bounds/clamping behaviors, or what the return value indicates about success or failure.

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 a single tight sentence that efficiently conveys the core action plus the essential coordinate-system clarification. Every word adds value. It could potentially add a brief note on alternatives or error conditions, but the current format is appropriately concise and front-loaded.

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?

For a gesture tool with 100% schema coverage and no output schema, the description adequately covers the main concerns: what it does, coordinate semantics, and the physical-pixel clarification. It's missing edge-case guidance (off-screen coordinates, minimal swipe distance to register, interaction with duration) but is reasonably complete for its complexity level.

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 100%, so the schema already documents all 6 parameters. The description adds value by clarifying that x1/y1/x2/y2 are physical pixels referencing device_page_source bounds, which goes beyond the schema's generic 'Start X coordinate' descriptions. However, duration's default value (500ms) is only in the schema, and the description doesn't add guidance on reasonable ranges or the effect of duration on swipe behavior.

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 verb (swipe), the resource (device screen), and the coordinate semantics (physical pixels from device_page_source bounds). It distinguishes itself from related tools like device_tap, device_scroll, and device_drag_drop by specifying swipe directionality with start/end coordinates. The mention of 'no scaling needed' adds a critical usability detail.

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 explains the coordinate system (physical pixels matching device_page_source bounds), which is essential context for correct invocation. However, it doesn't explicitly state when to prefer this over device_scroll, device_drag_drop, or the iOS-specific ios_swipe variants, nor when NOT to use it. The coordinate clarification helps but doesn't differentiate from alternative gesture tools.

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