Skip to main content
Glama

read_screen

Reads the Android phone screen as UI elements with IDs, text, and tap coordinates, so agents can inspect state before and after actions.

Instructions

Read what is on the phone screen as a list of UI elements with ids, text, and tap coordinates. Call this first and after every action to see the result. Element ids are only valid until the next read_screen. Elements can also show a field's error, its hint, a heading, a tooltip or a pane title; "(covered by ...)" means a tap there would land on something else. A toast that just showed is listed at the end.

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": "read_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the id-invalidation rule, explains the '(covered by ...)' marker meaning a tap would land on something else, and notes that a just-shown toast appears at the end. It also enumerates extra element types (error, hint, heading, tooltip, pane title). It says nothing about failure modes, device-connection preconditions, or output size, which leaves the safety/edge profile incomplete.

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?

The primary function and the call-cadence rule come first, then the id-lifetime caveat, then the edge-case legend. Every sentence adds distinct information and nothing is repeated from the schema or annotations.

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?

There is no output schema and no annotations, so the description must explain the returned structure itself, and it does: element ids, text, tap coordinates, extra semantic fields, and the trailing-toast convention. It is close to complete for an agent's needs, but omits what happens on failure or when the screen is unavailable.

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?

The tool takes zero parameters, so there is nothing to disambiguate; the baseline of 4 applies. The description correctly presents this as a call-with-no-arguments operation.

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 ('read what is on the phone screen') and pins down the exact return format: a list of UI elements with ids, text, and tap coordinates. That return-format detail implicitly separates it from image-based siblings like screenshot or browser_read, so an agent can pick it without opening the schema.

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?

Explicit invocation cadence: 'Call this first and after every action to see the result' gives a clear when-to-use rule, reinforced by the note that element ids expire on the next read. It stops short of naming a when-not case or pointing at alternative siblings (e.g. screenshot vs browser_read), which keeps it from a 5.

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