Skip to main content
Glama

iphone_screenshot

Read-onlyIdempotent

Capture the current iPhone screen as a JPEG in iOS points, so pixel positions can be sent directly to tap or swipe actions.

Instructions

Capture the current iPhone screen as a JPEG image scaled to iOS points, plus its size.

Because the image is in points, any pixel position in it can be passed unchanged to iphone_tap or
iphone_swipe. Use it to see visual content (images, colours, layout, games). To find buttons or read
text, iphone_ui_tree is cheaper and gives exact positions. Reads only; adds a note if the phone is locked.

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": "iphone_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
qualityNoJPEG quality from 20 to 95; lower is smaller and cheaper.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.2.0
    • addedInput schema / properties / quality / description
      Added value: +"JPEG quality from 20 to 95; lower is smaller and cheaper."
    • addedInput schema / properties / quality / maximum
      Added value: +95
    • addedInput schema / properties / quality / minimum
      Added value: +20
  2. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds behaviour the annotations do not cover: the coordinate space is in points and can be reused unchanged for tap and swipe, and a note is appended when the phone is locked. It also states what the result contains, namely the image plus its size.

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 definition is three short sentences, and it starts with the core fact that the output is a JPEG in points. Each sentence adds new information: what is returned, how the coordinates can be reused, and which sibling to use for cheaper text extraction. No sentence is wasted, and the guidance is not buried.

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?

For a one-parameter read tool, this covers what an agent needs: the output format, the coordinate system, how the result relates to other tools, and what happens when the phone is locked. There is no output schema, but the description already says the result includes the image and its size, so nothing critical is missing.

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 single quality parameter has 100% schema description coverage, including a default and range that explains the trade-off. The body adds meaning on how coordinates in the returned image map unchanged onto iphone_tap and iphone_swipe, which is stated explicitly. The description does not restate the quality parameter, but the schema already covers it fully.

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 ('Capture the current iPhone screen as a JPEG image') plus the concrete output detail ('scaled to iOS points, plus its size'). It also explicitly differentiates itself from the sibling iphone_ui_tree, so an agent can choose between them without opening either schema.

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?

Gives explicit when-to-use guidance: visual content such as images, colours, layout, games. It also gives an explicit when-not-to: for buttons or text use iphone_ui_tree, which is described as cheaper and giving exact positions. That is a named alternative with the condition that selects it.

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