Swipium

Overview Schema Source Related Servers Discussions Admin

Prepare a target device + app

qa_prepare_target

Prepares an Android emulator and app under test by binding or booting the device, configuring Metro and adb reverse, installing, launching, and verifying.

Instructions

Prepare an Android Emulator and the app under test: bind or boot the device, Metro + adb reverse for RN/Expo, install, launch, verify. One combined consent covers boot/install; long steps return a jobId. bindOnly stops after bind/boot.

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": {
      "sessionId": "<sessionId>"
    },
    "name": "qa_prepare_target"
  }
}

Input Schema

Name	Required	Description
`apk`	No
`avd`	No
`appId`	No
`force`	No
`device`	No	Target serial; required when >1 device is online.
`approve`	No
`bindOnly`	No	Bind/boot + adb reverse only.
`headless`	No	Boot the AVD headless (default true).
`consentId`	No
`sessionId`	Yes
`allowLaunchWithoutMetro`	No	Launch a debug RN/Expo build without Metro (may RedBox).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Beyond the annotations (non-read-only, non-destructive, non-idempotent) it discloses two genuinely useful traits: a single combined consent covers boot and install, and long-running steps return a jobId for polling. What gets overwritten on an existing install, and failure/recovery behavior, remain unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the outcome and followed by the pipeline steps and the two notable modes. The telegraphic style ("Metro + adb reverse for RN/Expo") costs a little readability but wastes no words.

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?

With no output schema, 11 parameters, and a mutating multi-step workflow, the description covers the happy path and the jobId return but omits error conditions, re-run semantics, and how force interacts with an existing device/install. Adequate, not 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?

Schema coverage is only 36% across 11 parameters, so the description should compensate more. It clarifies bindOnly and implies consent/approve behavior, but apk, avd, appId, force, consentId, and sessionId get no explanation in either the description or the schema.

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?

"Prepare an Android Emulator and the app under test" names a specific verb and resource, and the step list (bind/boot, Metro + adb reverse, install, launch, verify) makes the scope concrete. It is differentiated from the iOS sibling only implicitly through "Android".

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 gives one meaningful mode switch ("bindOnly stops after bind/boot"), implying when to use the short-circuit path. It does not say when to prefer this over qa_resolve_target, qa_build, or qa_metro, nor what prerequisites must be met before calling.

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