NoMac

Choose a cloud iPhone's Simulator

phone_device_use

Cloud iPhone: Choose the Simulator the other tools use, booting it if needed (one boot at a time), and optionally set dark or light appearance and a clean status bar (9:41, full battery) for screenshots.

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": "phone_device_use"
  }
}

Input Schema

Name	Required	Description
`device`	No	Name, name with runtime ("iPhone 17 Pro (iOS 27.0)") or UDID; default: the booted one, else the newest iPhone
`appearance`	No	Light or dark mode
`session_id`	No	The phone; default: the account's running phone
`status_bar`	No	clean: 9:41 and full bars; real: undo
`request_key`	No	Repeat a lost call with the same key

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 26, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations only say it is a non-read-only, non-idempotent, non-destructive mutation; the description adds real behavioral context beyond them: it boots the simulator if needed, booting is serialized ('one boot at a time'), and appearance/status bar changes are cosmetic and screenshot-oriented. It omits boot duration, failure modes, and the fact that status_bar=real undoes the clean state (left to 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?

A single dense sentence with the core action front-loaded ('Choose the Simulator the other tools use') followed by the optional side effects. Slightly run-on with nested parentheses, but no wasted sentences.

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?

For a 5-parameter, all-optional, no-output-schema selection tool, the description covers the essential behavior (boot-if-needed, serialized boots, cosmetic side effects). It could say more about what is returned (device identity/state) and what happens when the requested device isn't available, but the agent has enough to invoke it correctly.

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 description coverage is 100%, including precise device-defaulting rules and enum meanings, so the schema already carries the parameter semantics. The description only echoes the appearance and status-bar purposes ('dark or light', '9:41, full battery'), adding little beyond what structured fields provide.

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 ('Choose the Simulator the other tools use') and clarifies the tool's role as the device selector for subsequent calls, which is the key distinction from phone_devices. It doesn't explicitly name the sibling, but the actor/scope 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?

The phrase 'the Simulator the other tools use' implies this is a prerequisite step before other phone tools, and 'optionally set ... for screenshots' hints at a screenshot-prep use case. However, there is no explicit when-not guidance or naming of the alternative (phone_devices) when the agent only wants to enumerate devices.

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

All NoMac tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?