Skip to main content
Glama

Capture Adb Screen

capture_adb_screen

Captures a single ADB device screen frame as a PNG in a chosen local directory, then reports its dimensions and digest for verification.

Instructions

Capture one frame of the device screen as a PNG (screencap -p through exec-out, no device-side file) into a caller-selected output directory, digesting it and reporting its dimensions. No recording or interaction.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "serial": "emulator-5554",
      "output_directory": "/tmp/rea-captures"
    },
    "name": "capture_adb_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
serialYesDevice serial exactly as `adb devices` reports it
output_directoryYesLocal directory for the captured PNG; must not already contain it

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real behavioral detail beyond that: the capture is streamed via exec-out with no device-side file, a local PNG is written into the caller's directory, and the result is digested with dimensions reported — consistent with non-read-only and non-idempotent hints since a local file is produced and the call fails if it already exists.

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?

One front-loaded sentence carries the mechanism, destination, and outputs, with a short exclusion fragment at the end; nothing is redundant. The parenthetical and the verb 'digesting' are slightly dense, but no sentence is wasted.

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?

With no output schema, the description does the work of describing the return payload (digest plus dimensions), and both parameters are fully specified. The one remaining gap is that it never says what filename the PNG will take inside the given directory, which matters for a tool that errors when the directory 'must not already contain it'.

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 both `serial` and `output_directory` are already documented in the schema. The description restates 'caller-selected output directory' but adds no format, naming, or serial-matching detail beyond what the schema provides, making the baseline 3 correct.

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 specific verb and resource: capture one frame of the device screen as a PNG, with the underlying mechanism named (`screencap -p` via exec-out). It is clearly an Android/ADB screen capture and not a browser or native-UI scenario capture, though it never names a sibling tool to sharpen that 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?

The trailing clause 'No recording or interaction' implies this is a one-shot still capture rather than a recording or interactive session, which is mild negative guidance. There is no explicit when-to-use statement and no named alternative (e.g. capture_web_screenshot or capture_native_ui_scenario), so selection must be inferred from the tool name.

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