Skip to main content
Glama

adb_shell

Execute shell commands on an Android device and return stdout and stderr for direct diagnostics and automation via ADB.

Instructions

Execute a shell command on the Android device. Returns stdout and stderr.

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": {
      "command": "<command>"
    },
    "name": "adb_shell"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoDevice serial
commandYesShell command to execute on the device
timeoutNoTimeout in milliseconds (1s-10min)

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. Changed1 schema field changedv1.1.3
    • removedInput schema / additionalProperties
      Removed value: -false
  3. First observedv1.1.1

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden for a tool that runs arbitrary commands on a device. It only notes that stdout and stderr are returned; it says nothing about the destructive potential of arbitrary shell commands, default device selection when 'device' is omitted, timeout behavior on expiry, or whether output is truncated.

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 short sentences, action first, return value second, with no filler. Given the small amount of content, nothing is redundant and the key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a high-blast-radius, arbitrary-execution tool with no annotations and no output schema, yet the description is only two sentences. It omits safety posture, device targeting, timeout semantics, and result handling, all of which an agent needs before invoking it against a real device.

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 100%, with all three parameters documented including the millisecond range for timeout, so the schema does the parameter work. The description adds no meaning beyond the schema, such as what happens when 'device' is omitted or how timeout expiry is surfaced. Baseline 3 applies.

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?

States a specific verb (execute) and resource (a shell command on the Android device), plus the return payload (stdout and stderr). It does not distinguish itself from closely related siblings such as adb_root_shell, adb_multi_shell, or adb_qemu_guest_shell, so an agent cannot tell from the description alone which shell tool applies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, no mention of prerequisites such as root or device selection, and no pointer to the more specialized siblings that cover shell-like work. The agent must infer everything about applicability from the name.

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