Manos MCP

Overview Schema Source Related Servers Discussions Admin

Launch app

launch_app

Launch an app on a device by its bundle ID (iOS) or package name (Android). Optionally clear the app state before launching.

Instructions

Launch an app by bundle id (iOS) / package name (Android). Optionally clear state 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": {
      "device_id": "<device_id>",
      "app_id": "<app_id>"
    },
    "name": "launch_app"
  }
}

Input Schema

Name	Required	Description	Default
`app_id`	Yes
`observe`	No	What to return after the action: 'screen' = fresh compact hierarchy, 'diff' = only what changed since last inspect, 'screenshot' = PNG, 'none' = just confirm.	none
`device_id`	Yes	Device id from list_devices (adb serial like 'emulator-5554', or an iOS simulator UDID)
`clear_state`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Jul 31, 2026

TDQS

A3.5/5.0

Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits itself. It only mentions the optional clear state side effect, but does not disclose what happens if the app is already running, whether the tool waits for launch, or any error behavior. The return behavior is only indirectly addressed via the 'observe' parameter in the schema, leaving a notable transparency 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?

The description is a single sentence of 13 words, directly front-loaded with the action and platform specifics. There is no filler or repetition, every word earns its place.

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 4-parameter tool with no output schema, the description and schema together provide enough to invoke the tool. However, the description lacks information about error conditions, installation prerequisites, or timeouts. The observe parameter in schema covers return values, but the overall picture is only minimally complete.

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?

The description adds value by explaining app_id as 'bundle id (iOS) / package name (Android)', which is not in the schema, and clarifies clear_state. However, with schema coverage at 50%, the description only partially compensates; device_id and observe are already well-described in the schema, so the net contribution is moderate.

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 clearly states the tool's function: 'Launch an app by bundle id (iOS) / package name (Android).' This specific verb+resource distinguishes it from sibling tools like stop_app and open_deeplink, and the 'Optionally clear state first' clause adds further scope.

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?

The description implies the tool is used to launch a mobile app on a device, which is useful context. However, it does not explicitly mention when to prefer this over alternatives such as open_deeplink or stop_app, nor any exclusions. The 'optionally clear state first' gives some guidance but lacks explicit comparisons.

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