Skip to main content
Glama

adb_multi_test

Run diagnostic profiles or custom shell checks in parallel across all connected Android devices, then compare per-check results to spot matches and differences.

Instructions

Run a comparative test workflow across all connected devices (host + QEMU guests). Executes a predefined diagnostic profile or custom command list on every device in parallel, compares results per-check, and reports matches and differences. Profiles: 'firmware' (baseband, bootloader, kernel, security patch), 'security' (SELinux, verified boot, encryption), 'network' (radio, WiFi, SIM), 'identity' (model, chipset, architecture), 'full' (all profiles). Custom commands also supported.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "adb_multi_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
devicesNoDevice serials to target (omit for all online devices)
profileNoPredefined test profile to run. 'full' runs all profiles.
timeoutNoTimeout per command per device in ms (1s-60s, default 10s)
commandsNoCustom checks to run (max 50). Each has a label and command.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.6
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed2 schema fields changedv1.1.3
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / commands / items / additionalProperties
      Removed value: -false
  3. First observedv1.1.1

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose real behavior: execution is parallel across every device, comparison happens per-check, and the output distinguishes matches from differences. It does not warn that 'commands' are arbitrary shell commands (mutation risk), does not state permission or rooting requirements, and does not describe the result structure. Useful, but incomplete for an unannotated tool.

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?

The core action and its comparison semantics are front-loaded in the first two sentences, and the trailing profile catalog is dense but genuinely informative rather than padding. The profile list makes the entry long, but every clause contributes a distinct fact.

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 four-parameter, unannotated, output-schema-less tool, the definition covers what it does and the profile vocabulary well. It falls short on the return shape beyond 'matches and differences' and on the safety profile of running custom commands across many devices, both of which an agent needs before calling it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description earns above that by explaining what the enum values mean semantically: 'firmware' covers baseband/bootloader/kernel/security patch, 'security' covers SELinux/verified boot/encryption, and so on. That meaning is not in the schema, where the enum is a bare list. It does not add anything about the timeout or devices parameters.

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?

The description names a specific verb and resource: run a comparative test workflow across all connected devices (host + QEMU guests), executing profiles or custom commands and reporting matches/differences. That is far more specific than the bare name. It never names the adjacent siblings (adb_multi_shell, adb_multi_compare) that an agent would otherwise confuse it with, so differentiation stays implicit.

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 the phrase 'comparative test workflow' and by the profile list, which suggests when the tool is appropriate. There is no explicit when-to-use/when-not guidance and no alternative named, even though adb_multi_shell and adb_multi_compare sit in the same family and would be the obvious competitors.

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