Skip to main content
Glama

Start Adb App

start_adb_app
Destructive

Launch an installed Android app by package on a specified device and use the wait report to confirm whether its launcher activity started successfully for dynamic analysis.

Instructions

Start one installed app's resolved launcher activity with am start -W -n. A device-mutating tool for dynamic analysis. The full wait report determines success; failures retain launch-attempt facts and raw output. Pair with read_adb_logcat (pid filter) and list_adb_processes to observe the app, and stop_adb_app to end the run.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "serial": "emulator-5554",
      "package": "com.example.app"
    },
    "name": "start_adb_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
serialYesDevice serial exactly as `adb devices` reports it
packageYesInstalled package whose launcher activity is started

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructive, non-idempotent, open-world behavior, and the description goes beyond them by disclosing how success is judged (the full `am start -W` wait report) and how failures are reported (launch-attempt facts plus raw output retained). It does not cover prerequisites such as device authorization or what happens if the package lacks a launcher activity.

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?

Three tight sentences, front-loaded with the concrete action and command form, followed by outcome semantics and then related-tool routing. No filler, and each sentence carries distinct information.

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 destructive, non-idempotent launch tool with no output schema, the definition covers success criteria, failure reporting, and follow-up tools, which is nearly everything an agent needs to call it correctly. The remaining gap is behavior for edge cases like a missing or non-launchable package.

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 format of both parameters is already documented and baseline would be 3. The description adds meaning by requiring the package to be installed and noting that its launcher activity is resolved and started, which tells the agent something the schema alone does not about the package parameter's requirements.

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?

States a specific verb and resource plus the exact mechanism used (`am start -W -n`) and narrows the target to the package's resolved launcher activity, which implicitly separates it from starting an arbitrary activity. It does not name `start_adb_activity` explicitly, so the sibling differentiation is inferable rather than stated.

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?

Explicitly frames the tool as device-mutating for dynamic analysis and names concrete companions: `read_adb_logcat` with a pid filter and `list_adb_processes` for observation, `stop_adb_app` to end the run. It gives clear positive context but no explicit when-not-to-use case (e.g., when to prefer `start_adb_activity`).

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

Deploy Server

Other Tools