Skip to main content
Glama

Pull Adb Package

pull_adb_package

Pulls an installed Android package's full APK set (base and splits) from a device via ADB into a new package-named output subdirectory, with SHA-256 digests and partial-pull results.

Instructions

Pull one installed package's complete APK set (base plus every split, as pm path reports) from the device into a caller-selected output directory, creating a package-named subdirectory that must not already exist. Every pulled file is digested with SHA-256; partial pulls keep successful artifacts and per-file failure reasons. The device keeps the originals.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "serial": "emulator-5554",
      "package": "com.example.app",
      "output_directory": "/tmp/rea-pulls"
    },
    "name": "pull_adb_package"
  }
}

Input Schema

NameRequiredDescriptionDefault
serialYesDevice serial exactly as `adb devices` reports it
packageYesInstalled package name whose APK set is pulled
output_directoryYesLocal directory for the pulled APK set; REA creates a package-named subdirectory inside it

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that a package-named subdirectory is created and must not already exist, that each file is SHA-256 digested, that partial pulls retain successful artifacts with per-file failure reasons, and that the device keeps the originals. Notes idempotentHint=false is consistent with the 'must not already exist' precondition.

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?

Front-loaded with the core action and scope, then behavior. Dense but every clause carries information; the nested parenthetical about `pm path` is the only mildly awkward element.

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?

With no output schema, the description does supply return-relevant detail (per-file SHA-256 digests, partial-success semantics with per-file failure reasons). What remains thin is caller guidance on when this tool is the right choice among the many adb siblings.

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 100% and the schema already states that a package-named subdirectory is created inside output_directory, so the description mostly restates it. The added 'must not already exist' constraint is useful but small; serial and package semantics come entirely from the schema.

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 verb (pull), a precise resource (one installed package's complete APK set, base plus every split as `pm path` reports), and the output destination. This is materially distinct from the file-level sibling pull_adb_file.

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 implied by 'complete APK set' versus a single file, but the description never names when to prefer pull_adb_file or inspect_adb_package, and states no exclusions or preconditions for choosing this tool.

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

Deploy Server

Other Tools