Skip to main content
Glama

Robot Actions — Remote Device Control

ios_two_finger_tap

Two-finger tap at (x,y) on an iOS device — zooms OUT one step in Maps, acts as a secondary click in web views, and is the accessibility gesture in several Apple apps. Both fingers land either side of the point and lift without moving. holdMs turns it into a two-finger press-and-hold. Coordinates are screen points. Requires an active iOS automation session.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesTap centre X (screen points)
yYesTap centre Y (screen points)
normNoIf true, x/y (and path points) are 0..1 FRACTIONS of the screen — pass `pixelInScreenshot ÷ screenshotSize` directly (scale-free, matches the frontend, avoids point-guessing). Default false = iOS screen points.
udidYesiOS device UDID
inputNoInput path. 'auto' (default) drives the gesture through the automation session. 'hid' drives it through the direct input path instead, which needs no automation session — it reports 'no HID available' on iOS 17.x or with no tunnel.
holdMsNoHold both fingers down this long before lifting (default: 0)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / input
      Added value: +{
      +  "description": "Input path. 'auto' (default) drives the gesture through the automation session. 'hid' drives it through the direct input path instead, which needs no automation session — it reports 'no HID available' on iOS 17.x or with no tunnel.",
      +  "enum": [
      +    "auto",
      +    "hid"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / norm
      Added value: +{
      +  "description": "If true, x/y (and path points) are 0..1 FRACTIONS of the screen — pass `pixelInScreenshot ÷ screenshotSize` directly (scale-free, matches the frontend, avoids point-guessing). Default false = iOS screen points.",
      +  "type": "boolean"
      +}
  2. Added

TDQS

A3.5/5.0
Behavior2/5

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

Without annotations, the description carries the full burden of behavioral disclosure. It explains the gesture mechanics, holdMs behavior, and coordinate system, but it makes two inaccurate blanket claims: 'Coordinates are screen points' (ignoring `norm=true` which uses fractions) and 'Requires an active iOS automation session' (ignoring `input='hid'` which needs none). These contradictions undermine transparency and could mislead an agent about preconditions and coordinate handling.

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?

The description is compact at four sentences, front-loading the primary purpose, then mechanics, modifier, and requirements. No redundant or irrelevant detail; each sentence contributes useful information and the structure is logical.

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?

Given the tool's moderate complexity (6 params, no output schema, no annotations), the description covers the gesture behavior and prerequisites but misses important exceptions for the `norm` and `input` parameters. The misleading session requirement creates a gap, and a more complete description would mention that `norm=true` changes coordinate interpretation and that `input='hid'` bypasses the session requirement.

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 100%, so the baseline is 3. The description adds a slight clarification that holdMs makes it a press-and-hold and that x/y are screen points (already in schema), but it does not explain `norm` or `input` further, and it actually mischaracterizes coordinate semantics by ignoring the norm option. Thus it does not significantly add beyond the schema.

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?

The description clearly identifies the tool as a two-finger tap on an iOS device, specifying the verb (tap), resource (iOS device at x,y), and gesture mechanics ('both fingers land either side of the point and lift without moving'). This distinguishes it from single-finger taps (ios_tap) and two-finger swipe (ios_two_finger_swipe), even though it does not explicitly name alternatives.

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 description gives contextual examples of when the gesture is used (Maps zoom out, web secondary click, accessibility), which helps an agent infer suitable scenarios. However, it does not explicitly contrast alternatives like ios_tap or ios_two_finger_swipe, and it makes an unconditional statement 'Requires an active iOS automation session' that is contradicted by the schema's `input` parameter allowing 'hid' without a session, making the guidance partially misleading.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources