Skip to main content
Glama

Robot Actions — Remote Device Control

by com.robotactions.test
OverviewDiscussionsAdmin

Device two finger tap

device_two_finger_tap

Two-finger tap at (x,y) on an Android device — zooms OUT one step in Maps and is the accessibility/secondary gesture in several apps. Both fingers land either side of the point and lift without moving. Coordinates are PHYSICAL pixels.Pass input="hid" to require the virtual touchscreen: the gesture then reaches the app as real kernel input and fails loudly instead of silently falling back to injected input. That strict path used to be device_uhid_two_finger_tap, which stays callable under its old name.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesTap centre X
yYesTap centre Y
gapNoPixels between the two contacts (default: 120)
udidYesDevice serial number (UDID)
inputNoInput path. 'auto' (default) prefers the virtual touchscreen and falls back to injected input. 'hid' requires the virtual touchscreen and fails if the device does not provide one — use it when the gesture must be real kernel input or must fail loudly.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / input / description
      Previous value: -"Input path. 'auto' (default) prefers the virtual touchscreen and falls back to injected input. 'hid' requires the virtual touchscreen and fails if the device does not provide one — use it when the gesture must be real kernel input or must fail loudly."New value: +"Input path. 'auto' (default) prefers the virtual touchscreen and falls back to injected input. 'hid' requires the virtual touchscreen and fails if the device does not provide one — use it when the gesture must be real kernel input or must fail loudly."
  2. Changed1 schema field changed
    • changedInput schema / properties / input / description
      Previous value: -"Input path. 'auto' (default) prefers the virtual touchscreen and falls back to injected input. 'hid' requires the virtual touchscreen and fails if the device does not provide one — use it when the gesture must be real kernel input or must fail loudly."New value: +"Input path. 'auto' (default) prefers the virtual touchscreen and falls back to injected input. 'hid' requires the virtual touchscreen and fails if the device does not provide one — use it when the gesture must be real kernel input or must fail loudly."
  3. Changed1 schema field changed
    • addedInput schema / properties / input
      Added value: +{
+  "description": "Input path. 'auto' (default) prefers the virtual touchscreen and falls back to injected input. 'hid' requires the virtual touchscreen and fails if the device does not provide one — use it when the gesture must be real kernel input or must fail loudly.",
+  "enum": [
+    "auto",
+    "hid"
+  ],
+  "type": "string"
+}
  4. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare the generic safety profile (readOnly=false, destructive=false, idempotent=false); the description adds genuinely new behavior: auto mode silently falls back to injected input, hid mode fails loudly, and the rename from device_uhid_two_finger_tap. It also discloses the physical gesture mechanics (fingers land either side, lift without moving) that determine whether the tap is recognized.

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

Conciseness4/5

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

Purpose and gesture semantics are front-loaded and every clause carries information, including the migration note for existing callers. It is slightly over-stuffed — the hid paragraph restates much of the schema's enum description — and has a formatting glitch ('pixels.Pass') that hurts readability.

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

Completeness4/5

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

For a 5-parameter, no-output-schema input tool this covers purpose, gesture mechanics, coordinate units, input-path selection, and failure behavior, which is close to complete. It does not mention device state prerequisites (screen on, target app foregrounded) that would affect success.

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

Parameters4/5

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

Schema coverage is 100% so the baseline is 3, but the description adds meaning the schema lacks: coordinates are 'PHYSICAL pixels' (the schema only says 'Tap centre X/Y'), and it reinforces the input enum's fail-loud contract. The gap parameter is left entirely to the schema, so it isn't a full 5.

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

Purpose5/5

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

States a specific verb+resource ('Two-finger tap at (x,y) on an Android device') and immediately distinguishes itself from the single-finger tap and two-finger swipe siblings by describing the two-contact geometry. The Android qualifier also separates it from ios_two_finger_tap.

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

Usage Guidelines4/5

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

Gives concrete usage context — 'zooms OUT one step in Maps and is the accessibility/secondary gesture in several apps' — and explains when to pick the strict input='hid' path versus the default auto path. It does not explicitly say when to prefer this over device_tap or device_two_finger_swipe, so it falls short of full when/when-not routing.

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

All Robot Actions — Remote Device Control toolsInspect
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources