Skip to main content
Glama

android_key

Destructive

Send navigation and editing key presses to an Android phone over ADB, such as HOME, BACK, ENTER, TAB, DEL, and volume controls.

Instructions

Press a named navigation or editing key. ENTER may submit the focused form.

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": {
      "key": "<key>"
    },
    "name": "android_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYes
deviceNoOptional connected device id, connection serial or exact model. Overrides the selected/default phone for this call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.3

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description adds one genuinely useful behavioral fact — that ENTER may submit the focused form — which explains the side-effect risk. It does not cover other keys' side effects (e.g. BACK leaving an app, WAKEUP changing device state) or whether the call waits for the UI to settle.

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?

Two short sentences, front-loaded with the action and with zero redundant wording. The brevity is efficient rather than padded, though it borders on under-specified for a state-changing device tool.

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 two-parameter device-control tool with annotations present and no output schema, the definition covers the core action and one important side effect. It leaves gaps an agent would care about: what happens if no device is connected, whether the key is delivered to the foreground screen, and what the call returns or confirms.

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 50%: the device parameter is documented in the schema, and the key parameter is a self-documenting 13-value enum, so the description adds little beyond noting that keys are "named" and calling out ENTER specifically. Baseline 3 is appropriate given the enum carries most of the meaning.

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 gives a specific verb and resource ("Press a named navigation or editing key") and constrains the target to the enumerated key set, so it is distinguishable from coordinate-based siblings like android_tap and text-entry android_type. It stops short of naming those siblings explicitly, so an agent must infer the boundary.

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 only implied: use this for named system/editing keys rather than taps or typed text. There is no explicit when-to-use or when-not-to-use statement and no mention of prerequisites such as needing an active connection or a foreground app.

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