Skip to main content
Glama

adb_screencap_annotated

Capture an Android screenshot with numbered UI element bounding boxes and a text legend so LLM workflows can reference elements by number instead of coordinates.

Instructions

Take a screenshot with UI element bounding boxes and numbered labels composited directly onto the image. Returns the annotated PNG path plus a text legend mapping each element number to its identity. Ideal for LLM workflows that need to reference specific UI elements by number rather than by coordinates.

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_screencap_annotated"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoDevice serial
filenameNoOutput filename (default: annotated_<timestamp>.png)
clickableOnlyNoOnly annotate clickable/scrollable elements (default true — reduces visual noise)

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

A4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose the two-part return value (annotated PNG path plus a numbered legend) and the compositing behavior, but says nothing about side effects such as where the file is written, whether a connected device is required, or what happens on capture failure.

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 tight sentences, front-loaded with the action and then the return value, then the intended use case. No filler, no repetition of the tool name, and each sentence adds information an agent needs.

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 correctly explains the return payload (PNG path + legend), and the three parameters are fully covered by the schema. It is nearly complete for this complexity, missing only operational details like device-state prerequisites and output file location.

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% and every parameter (device, filename, clickableOnly) is documented in the schema, so baseline 3 applies. The description adds no extra meaning about parameter effects — for example, it does not explain how clickableOnly=false changes the legend or the visual density of the output.

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 opens with a specific verb+resource ("Take a screenshot") and immediately names the distinguishing feature — UI element bounding boxes with numbered labels composited onto the image. That feature set makes it unmistakably different from adb_screencap, adb_screen, and adb_ui_dump without needing to name them.

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?

It gives clear usage context ("Ideal for LLM workflows that need to reference specific UI elements by number rather than by coordinates"), which tells an agent when this beats a coordinate-based or plain-screenshot approach. It stops short of explicitly naming alternatives or exclusions such as using adb_screencap for a raw image or adb_ui_find for locating a single element.

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