rn-device-mcp

Overview Schema Source Related Servers Discussions Admin

Launch an app

android_launch_app

Launch an Android app on an emulator or connected device by package name. Optionally force-stop it first to relaunch the app for testing or debugging.

Instructions

Launches an app by package name. relaunch: true force-stops it first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "packageName": "<packageName>"
    },
    "name": "android_launch_app"
  }
}

Input Schema

Name	Required	Description
`serial`	No	adb serial (from android_devices). Default: the only online device.
`relaunch`	No
`packageName`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 4, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely useful context that relaunch force-stops the running instance first, which is a state-losing side effect. It still omits whether the call waits for the app to come up, what happens if the package is not installed, and how failures surface. Note the force-stop disclosure sits in mild tension with destructiveHint=false and would benefit from clarification.

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?

Two short sentences with no waste; the core action is front-loaded and only the non-obvious relaunch behavior is called out. Nothing could be removed without losing information.

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?

For a simple three-parameter launch tool with no output schema, the definition covers the essentials but leaves real gaps: package name format, the force-stop side effect's consequences, and failure/precondition behavior. An agent could call it correctly in the happy path but would be guessing at the edges.

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 only 33%: serial is documented in the schema, but relaunch and packageName have no schema descriptions. The description recovers the meaning of relaunch (force-stop before launch) and hints that packageName is a package identifier, but never states the expected format (e.g. com.example.app) or the fallback device behavior for serial beyond what the schema already says.

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 ("Launches an app") plus the key identifier ("by package name"), which is enough to distinguish it from android_stop_app, android_install_apk, and ios_launch_app. It does not explicitly contrast with those siblings, keeping it below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives no when-to-use guidance: no mention of needing an online device, that the app must already be installed, or when to prefer relaunch over a plain launch versus android_stop_app followed by launch. Usage is only implied by the tool name.

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