Skip to main content
Glama

phone_swipe

Drag from one point to another to operate sliders, dismiss items, or perform custom gestures on an Android device.

Instructions

Drag from one point to another (sliders, swipe-to-dismiss, custom gestures). from/to take the same targets as phone_tap.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "phone_swipe"
  }
}

Input Schema

NameRequiredDescriptionDefault
msNoduration, default 300
toYes
fromYes
afterNoreturn the updated element list afterwards (default true)
settleNomax ms to wait for the screen to stop changing before reading it (default 2500)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden. 'Swipe-to-dismiss' can be destructive (dismissing notifications, deleting list items) and the description never warns about irreversible consequences, permission needs, or what happens if the drag lands on the wrong target. It adds only use-case flavor, not behavioral context beyond what the schema's ms/after/settle fields already say.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action front-loaded, followed immediately by the target-format tip. No filler, no restatement of the title or name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter device-interaction tool with no annotations and no output schema, the description leaves important gaps: whether the gesture is verified, whether the drag can be destructive, and what the 'after' element list return looks like. The from/to reference is helpful, but the unannotated mutation risk is not addressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%: ms, after and settle are documented inline, while from/to are bare strings. The description partially compensates by stating that from/to accept the same targets as phone_tap, which gives the agent a way to learn the required format. That is real added meaning, but it depends on the agent already knowing phone_tap's target syntax.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Drag from one point to another') and gives concrete use cases (sliders, swipe-to-dismiss, custom gestures), which is more than a restatement of the name. The 'from/to take the same targets as phone_tap' clause points at a sibling's convention, aiding disambiguation. It does not explicitly distinguish itself from phone_scroll, the most confusable sibling, keeping it below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The parenthetical examples imply when this is appropriate (slider adjustment, dismissal gestures), but there is no explicit when-not guidance and no exclusion of phone_scroll for scrolling content. An agent must infer that this is for continuous drag gestures rather than scroll operations.

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