Skip to main content
Glama

android_screen

Read-onlyIdempotent

Reads accessible screen elements, labels, and coordinates from an Android device; returns a screenshot PNG explanation when elements cannot be accessed for coordinate control.

Instructions

Read accessible screen elements, labels and coordinates. If Android cannot read an animated/protected screen or exposes no elements, returns a mode:screenshot explanation and PNG for coordinate control. Normal results remain a JSON array.

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_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoOptional connected device id, connection serial or exact model. Overrides the selected/default phone for this call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.3

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: on animated/protected screens or empty element exposure it degrades to a mode:screenshot payload with a PNG for coordinate control, while normal results stay a JSON array. That dual return mode is exactly the kind of non-obvious trait an agent needs and cannot get from annotations.

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, front-loaded with the primary purpose and followed by the fallback case and the normal-case contrast. No filler wording; the only slight weakness is that the fallback detail is packed densely into one sentence.

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 carries the burden of explaining returns and does so for both modes (element JSON array vs. mode:screenshot plus PNG). Minor omissions remain, such as coordinate units and any cap on the number of elements returned, but nothing essential to calling the tool correctly is missing.

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?

There is a single optional 'device' parameter with 100% schema description coverage, so the schema already explains the override semantics fully. The description says nothing about device targeting, which is acceptable given the high coverage but adds no value. Baseline 3 applies.

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 ('Read accessible screen elements, labels and coordinates') and implicitly separates itself from android_screenshot by noting that normal results are a JSON element array rather than an image. It does not name any sibling explicitly, so an agent must infer the contrast, but the core purpose is unambiguous.

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?

Usage is implied rather than stated: an agent can infer this is the way to inspect the UI before acting, and the description explains what happens on screens that cannot be read. There is no explicit 'use this instead of android_screenshot when...' or prerequisite guidance, leaving the choice between the two read tools to inference.

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