Drag on Android display

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

Discloses the action is a long-press drag-and-drop and is capability-gated, which adds some behavioral context beyond annotations. However, it does not confirm whether the action is destructive or reversible, and annotations provide no destructive hint. The description is not contradictory but leaves gaps.

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?

Single sentence that efficiently conveys the core action. No extraneous text, but could benefit from structured breakdown of behavior and parameters.

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?

Despite having an output schema, the description does not mention what the tool returns. The complexity of drag-and-drop with coordinate objects and parameters is not fully addressed. The description is too brief for the tool's complexity.

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 only 40%, meaning only serial and displayId have descriptions in the schema. The description adds no parameter details, leaving the start, end, and durationMs parameters undocumented. The action description implies coordinates and duration, but specifics are absent.

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 indicates the tool performs a long-press drag-and-drop action, specifying the action type and scope ('on one logical display'). However, it does not differentiate from sibling tools like mobile_input_swipe or mobile_input_tap, which perform similar input actions.

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?

No guidance on when to use this tool versus alternatives. The phrase 'capability-gated' hints at a precondition but does not explain what the gate is or how to meet it. No exclusion criteria or alternative tool mentions.

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