Skip to main content
Glama

gesture

Simulate touch interactions on iOS, Android, desktop, or TV devices by sending pan, fling, swipe, pinch, rotate, transform, or drag actions with configurable origin, duration, and distance.

Instructions

Perform a structured pan, fling, swipe, pinch, rotate, transform, or drag gesture. Select the gesture kind, then provide only the inputs that apply to that kind. Times out after 90s.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesGesture variant.
udidNoiOS device UDID selector.
debugNoEnable debug diagnostics.
deltaNoMovement delta for pan or transform gestures.
runIdNoLease run identifier.
scaleNoPinch or transform scale.
deviceNoDevice name selector.
moveMsNoDrag movement duration.
originNoGesture origin point.
presetNoSwipe preset.
serialNoAndroid device or Vega VVD serial selector.
sourceNoDrag source @ref or selector.
targetNoAlias for deviceTarget on commands without a UI target field. Interaction commands reserve target for the UI element.
tenantNoRemote tenant identifier.
degreesNoRotation in degrees.
leaseIdNoExisting lease identifier.
sessionNoAgent-device session name.
distanceNoFling distance.
noRecordNoDo not record this action.
platformNoPlatform selector used to resolve a device.
directionNoFling direction.
durationMsNoPan/transform duration.
destinationNoDrag destination @ref or selector.
includeCostNoInclude per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.
deviceTargetNoDevice target form. Maps to the CLI --target flag.
pointerCountNoPan touch pointer count (1 or 2).
sourceHoldMsNoDrag activation hold duration.
responseLevelNoResponse verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.
mcpOutputFormatNoMCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.
destinationHoldMsNoHold before releasing at the destination.
androidDeviceAllowlistNoAndroid serial allowlist used for device resolution.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed8 schema fields changedv0.20.10
    • removedInput schema / properties / cwd
      Removed value: -{
      -  "description": "Working directory for command execution.",
      -  "type": "string"
      -}
    • removedInput schema / properties / daemonAuthToken
      Removed value: -{
      -  "description": "Remote daemon auth token.",
      -  "type": "string"
      -}
    • removedInput schema / properties / daemonBaseUrl
      Removed value: -{
      -  "description": "Remote daemon base URL.",
      -  "type": "string"
      -}
    • removedInput schema / properties / iosSimulatorDeviceSet
      Removed value: -{
      -  "description": "iOS simulator device-set path used for device resolution.",
      -  "type": "string"
      -}
    • removedInput schema / properties / iosXctestDerivedDataPath
      Removed value: -{
      -  "description": "Derived data path for external iOS XCTest runner execution.",
      -  "type": "string"
      -}
    • removedInput schema / properties / iosXctestEnvDir
      Removed value: -{
      -  "description": "Writable directory for iOS XCTest runner env overlays.",
      -  "type": "string"
      -}
    • removedInput schema / properties / iosXctestrunFile
      Removed value: -{
      -  "description": "Externally built iOS XCTest runner .xctestrun artifact path.",
      -  "type": "string"
      -}
    • removedInput schema / properties / stateDir
      Removed value: -{
      -  "description": "Agent-device state directory.",
      -  "type": "string"
      -}
  2. Changed1 schema field changedv0.20.9
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "apple",
      -  "android",
      -  "vega",
      -  "linux",
      -  "web",
      -  "ios",
      -  "macos"
      -]New value: +[
      +  "apple",
      +  "android",
      +  "harmonyos",
      +  "vega",
      +  "linux",
      +  "web",
      +  "ios",
      +  "macos"
      +]
  3. Changed6 schema fields changedv0.20.6
    • addedInput schema / properties / destination
      Added value: +{
      +  "description": "Drag destination @ref or selector.",
      +  "type": "string"
      +}
    • addedInput schema / properties / destinationHoldMs
      Added value: +{
      +  "description": "Hold before releasing at the destination.",
      +  "maximum": 10000,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "pan",
      -  "fling",
      -  "swipe",
      -  "pinch",
      -  "rotate",
      -  "transform"
      -]New value: +[
      +  "pan",
      +  "fling",
      +  "swipe",
      +  "pinch",
      +  "rotate",
      +  "transform",
      +  "drag"
      +]
    • addedInput schema / properties / moveMs
      Added value: +{
      +  "description": "Drag movement duration.",
      +  "maximum": 10000,
      +  "minimum": 16,
      +  "type": "integer"
      +}
    • addedInput schema / properties / source
      Added value: +{
      +  "description": "Drag source @ref or selector.",
      +  "type": "string"
      +}
    • addedInput schema / properties / sourceHoldMs
      Added value: +{
      +  "description": "Drag activation hold duration.",
      +  "maximum": 10000,
      +  "minimum": 1,
      +  "type": "integer"
      +}
  4. Changed8 schema fields changedv0.20.2
    • changedInput schema / properties / durationMs / description
      Previous value: -"Gesture duration in milliseconds."New value: +"Pan/transform duration."
    • addedInput schema / properties / durationMs / maximum
      Added value: +10000
    • changedInput schema / properties / durationMs / minimum
      Previous value: -0New value: +16
    • addedInput schema / properties / noRecord
      Added value: +{
      +  "description": "Do not record this action.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "apple",
      -  "android",
      -  "linux",
      -  "web",
      -  "ios",
      -  "macos"
      -]New value: +[
      +  "apple",
      +  "android",
      +  "vega",
      +  "linux",
      +  "web",
      +  "ios",
      +  "macos"
      +]
    • addedInput schema / properties / pointerCount
      Added value: +{
      +  "description": "Pan touch pointer count (1 or 2).",
      +  "maximum": 2,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / serial / description
      Previous value: -"Android serial selector."New value: +"Android device or Vega VVD serial selector."
    • removedInput schema / properties / velocity
      Removed value: -{
      -  "description": "Rotate gesture velocity.",
      -  "minimum": 0,
      -  "type": "integer"
      -}
  5. Changed3 schema fields changedv0.17.11
    • addedInput schema / properties / includeCost
      Added value: +{
      +  "description": "Include per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "ios",
      -  "macos",
      -  "android",
      -  "linux",
      -  "web",
      -  "apple"
      -]New value: +[
      +  "apple",
      +  "android",
      +  "linux",
      +  "web",
      +  "ios",
      +  "macos"
      +]
    • addedInput schema / properties / responseLevel
      Added value: +{
      +  "description": "Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.",
      +  "enum": [
      +    "digest",
      +    "default",
      +    "full"
      +  ],
      +  "type": "string"
      +}
  6. Changed1 schema field changedv0.17.7
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "ios",
      -  "macos",
      -  "android",
      -  "linux",
      -  "apple"
      -]New value: +[
      +  "ios",
      +  "macos",
      +  "android",
      +  "linux",
      +  "web",
      +  "apple"
      +]
  7. Changed5 schema fields changedv0.17.6
    • addedInput schema / properties / iosXctestDerivedDataPath
      Added value: +{
      +  "description": "Derived data path for external iOS XCTest runner execution.",
      +  "type": "string"
      +}
    • addedInput schema / properties / iosXctestEnvDir
      Added value: +{
      +  "description": "Writable directory for iOS XCTest runner env overlays.",
      +  "type": "string"
      +}
    • addedInput schema / properties / iosXctestrunFile
      Added value: +{
      +  "description": "Externally built iOS XCTest runner .xctestrun artifact path.",
      +  "type": "string"
      +}
    • addedInput schema / properties / mcpOutputFormat
      Added value: +{
      +  "description": "MCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.",
      +  "enum": [
      +    "optimized",
      +    "json"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "ios",
      -  "android",
      -  "macos",
      -  "linux",
      -  "apple"
      -]New value: +[
      +  "ios",
      +  "macos",
      +  "android",
      +  "linux",
      +  "apple"
      +]
  8. First observedv0.16.9

TDQS

B3.4/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions that the gesture is 'structured' and that it times out after 90 seconds, but it does not describe the actual effects on the device UI, whether the gesture is recorded or replayable, what response the caller can expect, or what happens on failure. This is a significant transparency gap for a tool that performs physical user interactions.

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 two sentences with no filler. The first sentence front-loads the tool's capabilities, and the second sentence delivers the essential selection rule and a timeout constraint that the schema cannot express.

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?

The tool is high-complexity with 31 parameters, multiple device selectors, and several overlapping gesture types. The rich schema descriptions compensate for much of the missing kind-to-parameter mapping, but the description itself leaves that mapping implicit and does not address when to choose this tool over the dedicated 'swipe' sibling. This is adequate but not complete.

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?

The input schema already documents all 31 parameters, so the baseline is 3. The description adds meaning beyond the schema by instructing the agent to provide only the inputs that apply to the selected gesture kind, which is critical conditional knowledge given the large number of gesture-specific parameters.

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?

The description uses a clear verb ('Perform') and lists the specific gesture kinds: pan, fling, swipe, pinch, rotate, transform, and drag. It does not fully distinguish the tool from the sibling 'swipe' tool, which creates some ambiguity about whether 'gesture' with kind=swipe or the dedicated 'swipe' tool should be used.

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 a clear usage pattern: select the gesture kind, then provide only the inputs that apply to that kind. However, it does not explain when to prefer this tool over specialized siblings like swipe, scroll, click, or longpress, nor does it state any exclusions or preconditions.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/callstack/agent-device'

If you have feedback or need assistance with the MCP directory API, please join our Discord server