Skip to main content
Glama

android_open_app

Destructive

Launch an installed Android app by package name in the current user and wait for launch status; use android_apps to find package names.

Instructions

Resolve and launch an installed app in the current Android user, waiting for Android launch status. Use android_apps to find package names. Later user interaction may change the foreground app.

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_open_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoOptional connected device id, connection serial or exact model. Overrides the selected/default phone for this call.
packageNameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.3

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare the write/state-changing profile (readOnlyHint=false, destructiveHint=true, openWorldHint=true, idempotentHint=false). The description adds behavior the annotations cannot convey: the call blocks and waits for Android launch status, and the foreground app may change afterwards. It does not explain what a failed launch status looks like, which is the remaining gap.

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 short sentences, each with a distinct job: what it does, how to get the argument, and a caveat about post-call state. The core action is front-loaded and nothing is wasted.

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 two-parameter, no-output-schema tool, this covers action, prerequisite lookup, device override (via schema), and the blocking behavior. The only shortfall is that 'launch status' is not described in terms of success or failure, which matters because there is no output schema to explain the return value.

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 50%: the device parameter is documented in the schema, while packageName has only a regex pattern and no prose. The description partially compensates by implying packageName must be an installed package and by pointing to android_apps for discovery, but it adds no format or resolution details beyond that. Baseline 3 fits when half the schema carries the burden.

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?

States a specific compound verb (resolve and launch) against a specific resource (an installed app) and narrows scope to the current Android user. It also names the sibling tool (android_apps) that handles the adjacent lookup task, so an agent can place it precisely among the siblings.

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?

Gives concrete routing guidance: use android_apps to find package names before calling this. It also warns that later user interaction may change the foreground app, which tells the agent not to rely on the launched app persisting. It does not state explicit when-not-to-use conditions, so it stops short of a 5.

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