device_swipe

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It provides important behavioral details: coordinates must come from the physical screenshot, and on Android it automatically scales coordinates when a display override is detected. This reveals meaningful platform-specific behavior beyond the raw schema, though it doesn't mention return values or error behavior.

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 two sentences, with the core action front-loaded ('Swipe from (x1,y1) to (x2,y2)'), followed by the use case and a single coordinated note on coordinates and scaling. Every sentence earns its place, and there is no redundant wording.

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 low-level gesture tool with no output schema and no annotations, the description covers the core action, coordinate source, platform scaling, and use cases. It doesn't explain return values or error handling, but those are less critical for a raw coordinate swipe. The context provided is sufficient 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?

The description adds meaning to the coordinate parameters by tying them to the physical screenshot's originalWidth/originalHeight, and explains Android's automatic coordinate scaling. This supplements the schema's 'original screen pixels' descriptions, and the coverage was already at 71%. The remaining parameters (deviceId, platform, duration) are either self-explanatory or have schema descriptions.

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 a specific verb ('Swipe') and resource (from (x1,y1) to (x2,y2)), and distinguishes itself from sibling tools by explicitly labeling it 'Low-level' and targeting 'custom gestures or when you need precise swipe control'. This makes it clear how it differs from higher-level tools like device_tap or device_pinch.

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 direct usage guidance: 'Use this for custom gestures or when you need precise swipe control.' It implies this is not for ordinary interactions that higher-level tools handle, though it does not explicitly name alternatives or state when not to use it. The positive condition is clear, so this earns a 4 rather than a 5.

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