Skip to main content
Glama

Robot Actions — Remote Device Control

device_screenshot

Take a screenshot of a device (one frame). Returns the JPEG image PLUS, by default, a compact list of labeled UI elements with their bounds (in device-tap coord space — use directly with device_tap, no scaling). The bundled element list eliminates the second roundtrip to device_page_source and removes visual-estimation guesswork for tap targets that appear in the accessibility tree. Prefer device_tap_by_text for elements with a visible label; use these bounds only as a fallback. For continuous observation or debugging a stuck flow, use android_video_stream (live MJPEG) instead of polling screenshots. Set includeElements=false to skip the page-source fetch and return only the image. For routine per-action screen checks, android_mjpeg_screenshot is much faster — it reads the already-running video stream instead of taking a fresh capture, and bundles no element list; reserve this tool for when you need the labeled elements or a full-fidelity frame.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
udidYesDevice serial number (UDID)
includeElementsNoInclude the compact labeled-element list alongside the image (default: true). Set false to save tokens on screens you only need to look at, not interact with.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return format (JPEG plus element list), the coordinate space for bounds, the optional includeElements flag to skip page-source fetch, and performance trade-offs versus mjpeg. It doesn't detail potential side effects or error cases, but these are minimal for a screenshot tool. The description adds substantial behavior context beyond the schema.

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 description is longer than typical but every sentence contributes useful information. It is front-loaded with the core purpose and then expands on specifics and alternatives. The structure is logical and avoids fluff, though it could be slightly tighter without losing meaning.

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

Completeness5/5

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

Given there is no output schema, the description fully explains what the tool returns (JPEG image and labeled element list with bounds) and the coordinate space. It also covers the includeElements option and alternatives, providing a complete picture for an agent to use the tool correctly without missing critical context.

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% (both udid and includeElements have descriptions). The description adds value by explaining the trade-off of includeElements (skip page-source fetch, save tokens) and clarifies when to set it false. This goes beyond the schema's simple description, enhancing parameter understanding.

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?

The description clearly states the tool takes a screenshot of a device (one frame) and distinguishes it from siblings like android_mjpeg_screenshot and android_video_stream by highlighting the bundled element list feature. The verb 'take' and resource 'screenshot' are specific, and the additional element list sets it apart from other screenshot tools.

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

Usage Guidelines5/5

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

The description explicitly provides usage guidance: prefer device_tap_by_text for visible labels, use bounds as fallback; for continuous observation or stuck flows, use android_video_stream; for routine screen checks, use android_mjpeg_screenshot. It clearly states when to use this tool vs alternatives, leaving no ambiguity.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources