Skip to main content
Glama
Sign In
adb-ai

adb-ai

by cyberpunk2183
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

adb_key

Send ordered remote-control key presses to Android TVs, boxes, phones, or tablets over ADB to navigate menus, enter text, and control playback.

Instructions

Press remote-control keys, in order. Names: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, apps, back, blue, captions, channeldown, channelup, delete, down, enter, forward, green, guide, home, info, input, left, menu, mute, next, notifications, ok, pause, play, playpause, power, prev, record, red, rewind, right, search, settings, sleep, space, stop, tab, tv, up, voldown, volup, wake, yellow

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": {
      "keys": "<keys>"
    },
    "name": "adb_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysYese.g. ["home"], ["down","down","ok"]
deviceNoserial, ip[:port] or saved alias; omit to use the default device
repeatNopress each key N times
pace_msNoall the keys go in one call by default; set this (e.g. 120) if a menu drops keys that arrive back to back

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the key ordering behavior and enumerates the valid key names, which is meaningful beyond the schema. It does not say what happens on an invalid key name, whether the call blocks until the press completes, or what is returned.

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 behavioral statement is front-loaded in one short clause, and the long key enumeration earns its space because it is the only place valid values are documented. Structure is clear, though the enumeration could have been formatted as a labeled list for faster scanning.

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 4-parameter, annotation-free tool with no output schema, the definition covers inputs well but omits error behavior, return value, and the boundary versus adb_power/adb_volume/adb_tap. Adequate to invoke, incomplete for confident selection.

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 baseline is 3. The description goes further by supplying the canonical list of valid key strings, which the schema leaves as an unconstrained string array with no enum — that is genuine added meaning where the schema is weakest.

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 and resource ('Press remote-control keys') plus the ordering semantic, so the agent knows exactly what the tool does. However it never distinguishes itself from siblings with overlapping capability (adb_tap, adb_power, adb_volume) even though the key list includes 'power', 'volup/voldown', 'wake' and 'sleep'.

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?

No statement of when to prefer this over adb_tap, adb_type_text, adb_power or adb_volume, and no prerequisites (device connection, focus requirements). The only conditional guidance lives in the pace_ms schema field, not the description.

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