Skip to main content
Glama

Simulate an incoming call or SMS on an Android emulator over adb

telephony
Destructive

Simulate incoming calls and SMS on an Android emulator over adb to test app behavior, including ringing, accepting or canceling calls, and receiving texts.

Instructions

Simulate an incoming phone call or SMS on an Android emulator through its console over adb: call rings from the number, accept answers, cancel ends the call, and sms delivers a text message. The call screen or notification can cover the app and invalidate earlier UI observations. Times out after 90s.

Input Schema

NameRequiredDescriptionDefault
textNoMessage text for sms; required for sms and refused for the call actions. The emulator drops characters outside the Basic Multilingual Plane, such as emoji.
udidNoApple device or simulator UDID.
actionYescall starts an incoming call, accept answers it, cancel ends it, sms delivers a text message.
deviceNoDevice name; ids go in udid or serial.
numberYesCaller or sender phone number: digits with an optional leading +.
serialNoAndroid, HarmonyOS, or Vega VVD serial.
sessionNoSession name.
noRecordNoDo not record this action.
platformNoDevice platform.
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. Changed15 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."
    • changedOutput schema / (root)
      Previous value: -{
      -  "oneOf": [
      -    {
      -      "properties": {
      -        "action": {
      -          "enum": [
      -            "call",
      -            "accept",
      -            "cancel"
      -          ],
      -          "type": "string"
      -        },
      -        "message": {
      -          "type": "string"
      -        },
      -        "number": {
      -          "type": "string"
      -        }
      -      },
      -      "required": [
      -        "action",
      -        "number",
      -        "message"
      -      ],
      -      "type": "object"
      -    },
      -    {
      -      "properties": {
      -        "action": {
      -          "const": "sms",
      -          "type": "string"
      -        },
      -        "message": {
      -          "type": "string"
      -        },
      -        "number": {
      -          "type": "string"
      -        },
      -        "textLength": {
      -          "description": "Length of the delivered message text.",
      -          "type": "number"
      -        }
      -      },
      -      "required": [
      -        "action",
      -        "number",
      -        "textLength",
      -        "message"
      -      ],
      -      "type": "object"
      -    }
      -  ],
      -  "type": "object"
      -}New value: +null
  3. Addedv0.21.29

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already flag a non-read-only, destructive operation, and the description adds real behavioral context on top: the call screen or notification can cover the app and invalidate earlier UI observations, and the call times out after 90s. That is information an agent cannot get from the annotations. It stops short of saying what happens if accept/cancel is issued with no active call, or that an emulator/device must already be targeted.

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?

Three tight sentences, front-loaded with purpose, then the side effect, then the timeout — good ordering with no filler. The only mild redundancy is the action-mode recap, which duplicates the schema's enum description almost verbatim.

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?

No output schema exists, so the description must carry the behavioral burden, and it does cover the key surprises (UI occlusion, 90s timeout) for a 10-parameter tool whose fields are fully documented. Remaining gaps — error behavior for out-of-order actions and the Android-only framing versus schema fields for apple/ios/udid — are minor but real.

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 description coverage is 100%, so the schema already documents action, number, text, and the device-targeting fields; baseline is 3. The description's action breakdown largely restates the schema's own enum description ('call starts an incoming call, accept answers it…'), adding only the framing that 'number' is the caller/sender and 'text' the SMS body. No new semantics for the device-selection parameters.

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 opens with a concrete verb and resource ('Simulate an incoming phone call or SMS on an Android emulator through its console over adb') and then disambiguates all four action modes: call rings, accept answers, cancel ends, sms delivers. The bare name 'telephony' is rescued entirely by this text, and an agent can tell exactly what the tool does 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 context is implied rather than stated: adb console simulation on an emulator tells a knowledgeable agent this is for inbound-call/SMS test scenarios, but there is no explicit 'use this when…' versus an alternative, and no stated prerequisites (device connected, emulator running, call in progress for accept/cancel). The sibling list contains no obvious alternative for telephony, so the omission is tolerable but still a gap.

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