qa-mcp-server

Overview Schema Source Related Servers Discussions Admin

launch_app

Start an installed Android app and report launch state (COLD/WARM/HOT) plus TotalTime, so QA can measure startup performance and verify the app opens correctly.

Instructions

Start an installed app (launcher activity unless activity is given).

    Reports launch state (COLD/WARM/HOT) and TotalTime from `am start -W`.

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": {
      "package": "<package>"
    },
    "name": "launch_app"
  }
}

Input Schema

Name	Required	Description
`serial`	No
`package`	Yes	Android application id, e.g. org.example.app
`activity`	No

Output Schema

Name	Required	Description	Default
`serial`	Yes
`status`	Yes
`dry_run`	Yes
`component`	Yes
`launch_state`	No
`total_time_ms`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 13, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds real behavioral context: which activity is started by default, that launch state (COLD/WARM/HOT) and TotalTime are reported, and that it wraps `am start -W` — though it says nothing about failure when the package is not installed or about launch wait/timeout behavior.

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 sentences, both load-bearing, with the core action and its default behavior front-loaded and the return signal in the second line. No filler or restatement of the tool name.

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 simple three-parameter tool with annotations and an output schema, the description covers purpose, default activity resolution, and result semantics. Gaps are modest: error behavior for a missing package and multi-device serial guidance are unstated, and the return-value sentence slightly duplicates the output schema.

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 only 33%, so the description should compensate more than it does — `package` and `serial` receive no mention at all. It does add genuine meaning for `activity` by stating the launcher-activity fallback when it is omitted, which goes beyond the schema's bare 'fully qualified or relative' wording.

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?

Specific verb plus resource: 'Start an installed app', with the default resolution rule (launcher activity unless `activity` is given) stated up front. The word 'installed' implicitly separates it from install_apk, but no sibling is named explicitly, keeping it just short of 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 Guidelines3/5

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

Usage is only implied: the 'installed app' qualifier hints that installation must precede launching, but there is no explicit when-to-use framing, no mention of ordering relative to install_apk, and no guidance on device selection when `serial` is omitted. Adequate but leaves the agent to infer the workflow.

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

Deploy Server