Skip to main content
Glama
Sign In
run-sequence-android-mcp

run-sequence-android-mcp

by nasiosheva
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Start Screen Recording

android_start_recording

Start background screen recording on an Android device for later review or debugging, with automatic stop at 180 seconds or a chosen time limit.

Instructions

Start recording the device screen in the background. Stop it with android_stop_recording. Max duration is 180 seconds (Android limit).

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": "android_start_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoDevice id (serial or host:port). Optional -- when omitted, uses ANDROID_MCP_DEVICE env or auto-selects the connected device (physical devices preferred over emulators).
maxSizeNoMaximum video dimension in pixels, e.g. 480.
timeLimitNoAuto-stop after this many seconds. Defaults to 180 (maximum).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the load, and it does disclose two meaningful traits: recording happens in the background (asynchronous, not a blocking call) and is hard-capped at 180 seconds by an Android limit. It says nothing about permissions, what happens if a recording is already running, or where the resulting file lives, which is a notable gap for a stateful mutation 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?

Three short sentences with the core action front-loaded and zero filler. The stop pairing and duration limit follow in useful order, though the parenthetical '(Android limit)' is a minor redundancy with the timeLimit description.

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?

There is no output schema, so the description is the only place an agent could learn what starting a recording returns (a handle, a file path, or nothing) and how to retrieve the finished video. It covers start/stop lifecycle and duration but leaves the result-retrieval story entirely unspecified for a long-running stateful operation.

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%, so all three parameters (device, maxSize, timeLimit) are already documented in schema. The description only restates the 180-second ceiling that timeLimit already encodes, adding no new meaning such as units, format, or defaults beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start recording the device screen') plus a distinguishing trait ('in the background'). It also names the paired sibling android_stop_recording, so an agent can immediately tell this is the start side of a recording lifecycle rather than a screenshot capture.

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

Usage Guidelines4/5

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

Gives clear context for use by pairing it with android_stop_recording and warning about the hard 180-second cap. It does not explicitly contrast with android_take_screenshot or android_save_screenshot, so an agent choosing between still capture and video capture gets only an implied distinction.

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