Skip to main content
Glama

adb_screenrecord_start

Start an on-device screen recording on a connected Android device, then use the stop tool to finish and retrieve the video file.

Instructions

Start recording the device screen. Recording runs on-device. Use adb_screenrecord_stop to finish and pull the video file.

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": "adb_screenrecord_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoDevice serial
maxDurationNoMaximum recording duration in seconds (1-180, default 60)

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

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. "Recording runs on-device" is useful behavioral context implying the file lives on the device until stop pulls it, but it omits permission requirements, whether a second start fails or errors while a recording is active, and what start returns (a handle, path, or nothing).

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?

Three short sentences, front-loaded with the action, then the architectural fact, then the required follow-up. Nothing is redundant and no sentence could be dropped without losing information.

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

Completeness4/5

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

For a start/stop pair with no output schema and fully documented parameters, the description covers the essential lifecycle and the on-device storage detail. The remaining gap is what start itself returns, which matters for an agent that must correlate the start handle with the later stop call.

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 100%, so both device and maxDuration are already documented in the schema, including the 1-180 range and default 60. The description adds no meaning beyond that baseline, which is acceptable at full coverage but earns nothing extra.

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?

"Start recording the device screen" gives a specific verb and resource, and the mention of adb_screenrecord_stop as the terminator clarifies this is the first half of a capture workflow. It is distinguishable from adb_screencap (single frame) by the word "recording," though it never names that sibling explicitly.

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?

It clearly states the required follow-up call (adb_screenrecord_stop) to finish and pull the file, which is genuine sequencing guidance. However, it gives no guidance on when to record versus taking a screenshot or starting a mirror session, and no prerequisites such as a connected device or concurrent-recording limits.

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