Skip to main content
Glama

adb_input

Send tap, swipe, text, and keyevent input to an Android device through ADB to automate UI interaction and device control.

Instructions

Send input events to the device (tap, swipe, text, keyevent)

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": {
      "type": "<type>",
      "args": "<args>"
    },
    "name": "adb_input"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsYesArguments: tap='x y', swipe='x1 y1 x2 y2 [duration_ms]', text='string', keyevent='KEYCODE_HOME'
typeYesInput type — one of: tap (single touch), swipe (drag between two points), text (literal string entry), keyevent (Android key code like KEYCODE_HOME). The args field documents the expected argument format per type.
deviceNoDevice serial

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
    • changedInput schema / properties / type / description
      Previous value: -"Input type"New value: +"Input type — one of: tap (single touch), swipe (drag between two points), text (literal string entry), keyevent (Android key code like KEYCODE_HOME). The args field documents the expected argument format per type."
  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?

With no annotations supplied, the description carries the full behavioral burden, yet it only says that events are injected. It does not disclose that this mutates live UI state, whether coordinates are pixels relative to the current screen, how special characters in 'text' must be escaped, or how failures/blocking behave.

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 single sentence is front-loaded with the action and immediately scopes it with the supported types; there is no wasted wording. Its brevity is efficient, though it borders on under-specification for a state-mutating tool.

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?

For a parameter-light but side-effecting tool with no annotations and no output schema, the description leaves out what the agent most needs: confirmation of success/failure, device-selection behavior, and overlap with the specialized input siblings. The complete schema partially compensates, but the behavioral picture remains thin.

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%, and the schema already details the exact argument format per input type and the enum semantics. The description's parenthetical list of types merely repeats the enum values, adding no syntax or format detail beyond what the schema provides.

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 states a concrete verb and resource ('Send input events to the device') and names the four event types, so an agent knows exactly what the tool does. It does not, however, distinguish this general tool from overlapping siblings such as adb_input_text, adb_input_drag, adb_input_long_press, or adb_tap_element, which an agent must choose between.

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 guidance on when to prefer this generic input tool over the many specialized siblings (adb_input_text for typing, adb_input_drag for swipes, adb_tap_element for UI-element taps). No prerequisites, exclusions, or context about device targeting are given, leaving the choice entirely to inference.

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