Skip to main content
Glama

Inspect, accept, or dismiss a platform alert

alert
Destructive

Inspect, wait for, accept, or dismiss platform permission prompts on iOS, Android, and desktop devices to automate dialog handling.

Instructions

Inspect, wait for, accept, or dismiss a platform alert. The get action reads alert content; accept and dismiss change the active alert state. Each iOS XCTest execution activates once, then only observes. Apple XCTest and Limrun iOS choose recognized English labels by preference (Allow While Using App before Allow Once); on iOS simulators, including Limrun, the runner also recognizes the device's preferred languages' wording of those labels from the OS permission-prompt strings, on any alert; equal-ranked choices and unknown labels refuse, including a lone unknown button. Open, Done, and Confirm… accept; Keep Browsing, Deny, and Skip dismiss. On the Apple XCUITest runner, dismiss taps only a recognized decline label (Cancel, Don't Allow, Ask App Not to Track, and similar) or the close element of a popover whose accessibility marker reads exactly "dismiss popup"; when no button fits the action, accept and dismiss answer ALERT_BUTTON_NOT_FOUND having tapped nothing. The get action exposes labels for explicit button targeting. The timeout argument is the poll window only for wait: a wait polls its whole window, accepted up to 2147453647 ms, and a longer one is refused before anything runs with details.reason: alert-wait-window-too-long and details.maxWaitWindowMs, never shortened. On the Apple XCUITest runner, get takes the same argument as the runner's read budget (10 s by default, at least 1.5 s, at most 25 s); other backends' get ignores it. For wait, the first XCTest read uses the requested window capped at 25 s; later reads use the remaining window with the same cap, without the 1.5 s floor. Every backend's accept and dismiss run their own retry window and ignore the argument. A get the runner's watchdog (the same budget) cuts off answers runner_main_thread_timeout with dispatched: unknown, which does not mean no alert; the next get waits out RUNNER_BUSY while abandoned work drains, and still answers RUNNER_BUSY (dispatched: no) if that outlasts the bounded resends. A get result with status none reports no alert. An alert-not-found refusal means no alert was found and no button was pressed. An alert-wait-timeout means no actionable alert resolved within the wait window. A refusal with dispatched: no means no button was activated. After a press, an unconfirmed outcome leaves the resulting alert state unknown. Times out after 90s; a caller-supplied budget extends it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "alert"
  }
}

Input Schema

NameRequiredDescriptionDefault
udidNoApple device or simulator UDID.
actionNo
deviceNoDevice name; ids go in udid or serial.
serialNoAndroid, HarmonyOS, or Vega VVD serial.
sessionNoSession name.
noRecordNoDo not record this action.
platformNoDevice platform.
timeoutMsNo
deviceTargetNoDevice form factor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.21.38
    • removedInput schema / properties / debug
      Removed value: -{
      -  "description": "Enable debug diagnostics.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / includeCost
      Removed value: -{
      -  "description": "Add agent cost (cost.wallClockMs, …) to the result, returned as JSON text.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / mcpOutputFormat
      Removed value: -{
      -  "description": "Result text: compact optimized (default) or the full result as JSON (larger).",
      -  "enum": [
      -    "optimized",
      -    "json"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / responseLevel
      Removed value: -{
      -  "description": "Result detail: digest (smallest) or full (largest), as JSON; default is compact text.",
      -  "enum": [
      -    "digest",
      -    "default",
      -    "full"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / target
      Removed value: -{
      -  "description": "Alias for deviceTarget.",
      -  "enum": [
      -    "mobile",
      -    "tv",
      -    "desktop"
      -  ],
      -  "type": "string"
      -}
  2. Changed14 schema fields changedv0.21.37
    • removedInput schema / properties / androidDeviceAllowlist
      Removed value: -{
      -  "description": "Android serial allowlist used for device resolution.",
      -  "type": "string"
      -}
    • changedInput schema / properties / device / description
      Previous value: -"Device name selector (a UDID belongs in udid, a serial in serial)."New value: +"Device name; ids go in udid or serial."
    • changedInput schema / properties / deviceTarget / description
      Previous value: -"Device target form. Maps to the CLI --target flag."New value: +"Device form factor."
    • changedInput schema / properties / includeCost / description
      Previous value: -"Include per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged."New value: +"Add agent cost (cost.wallClockMs, …) to the result, returned as JSON text."
    • removedInput schema / properties / leaseId
      Removed value: -{
      -  "description": "Existing lease identifier.",
      -  "type": "string"
      -}
    • changedInput schema / properties / mcpOutputFormat / description
      Previous value: -"MCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately."New value: +"Result text: compact optimized (default) or the full result as JSON (larger)."
    • changedInput schema / properties / platform / description
      Previous value: -"Platform selector used to resolve a device."New value: +"Device platform."
    • changedInput schema / properties / responseLevel / description
      Previous value: -"Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged."New value: +"Result detail: digest (smallest) or full (largest), as JSON; default is compact text."
    • removedInput schema / properties / runId
      Removed value: -{
      -  "description": "Lease run identifier.",
      -  "type": "string"
      -}
    • changedInput schema / properties / serial / description
      Previous value: -"Android, HarmonyOS, or Vega VVD serial selector."New value: +"Android, HarmonyOS, or Vega VVD serial."
    • changedInput schema / properties / session / description
      Previous value: -"Agent-device session name."New value: +"Session name."
    • changedInput schema / properties / target / description
      Previous value: -"Alias for deviceTarget on commands without a UI target field. Interaction commands reserve target for the UI element."New value: +"Alias for deviceTarget."
    • removedInput schema / properties / tenant
      Removed value: -{
      -  "description": "Remote tenant identifier.",
      -  "type": "string"
      -}
    • changedInput schema / properties / udid / description
      Previous value: -"Apple device or simulator UDID; the selector that pins one device when several share a name."New value: +"Apple device or simulator UDID."
  3. Changed3 schema fields changedv0.21.0
    • changedInput schema / properties / device / description
      Previous value: -"Device name selector."New value: +"Device name selector (a UDID belongs in udid, a serial in serial)."
    • changedInput schema / properties / serial / description
      Previous value: -"Android device or Vega VVD serial selector."New value: +"Android, HarmonyOS, or Vega VVD serial selector."
    • changedInput schema / properties / udid / description
      Previous value: -"iOS device UDID selector."New value: +"Apple device or simulator UDID; the selector that pins one device when several share a name."
  4. 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"
      -}
  5. 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"
      +]
  6. Changed3 schema fields changedv0.20.2
    • 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"
      +]
    • changedInput schema / properties / serial / description
      Previous value: -"Android serial selector."New value: +"Android device or Vega VVD serial selector."
  7. 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"
      +}
  8. 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"
      +]
  9. 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"
      +]
  10. First observedv0.16.9

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description goes far beyond that with per-backend press semantics, the exact label taxonomy for accept vs dismiss, refusal codes (ALERT_BUTTON_NOT_FOUND), the dispatched: no/unknown distinction, RUNNER_BUSY retry behavior, watchdog cutoff, and the 90s ceiling. This is exactly the behavioral context a destructive multi-backend tool needs.

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

Conciseness3/5

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

The content is dense and mostly earns its place, but it is delivered as a single unbroken block of run-on sentences, e.g. the watchdog/RUNNER_BUSY sentence is very hard to parse on first read. The core purpose is front-loaded, yet the timeout and error-code material would be far more scannable as structured bullets.

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

Completeness5/5

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

With nine optional parameters, no output schema, and destructive side effects across five backends, the description supplies the missing pieces: return statuses (status none, alert-wait-timeout), refusal semantics, what happens when nothing is tapped, and the post-press unknown-outcome caveat. Nothing an agent needs to call this safely appears absent.

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 78%, and the one parameter with no schema description (timeoutMs) is fully explained: it is a poll window for wait only, capped at 25s per read with no 1.5s floor after the first read, accepted up to 2147453647 ms with a named refusal reason, treated as a read budget for XCUITest get, and ignored by accept/dismiss and other backends' get. The remaining parameters (udid, serial, platform, etc.) are already documented in the schema and are not restated.

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 opening sentence names a specific resource (platform alert) and enumerates all four verbs (inspect/wait/accept/dismiss), then immediately splits them by effect: 'get reads alert content; accept and dismiss change the active alert state.' An agent can tell this apart from generic siblings like get, wait, or press without opening the schema.

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?

Usage is implied rather than prescribed: 'The get action exposes labels for explicit button targeting' suggests a get-then-target workflow, and the label lists (Allow While Using App, Cancel, Don't Allow, etc.) tell the agent what each action will actually hit. But there is no explicit 'use this instead of press/wait when…' routing against the many sibling tools, so the agent must infer the boundary itself.

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