Skip to main content
Glama

iphone_close_app

DestructiveIdempotent

Force-quit a specified iPhone app to reset it or stop it running. Use when an app must be restarted; unsaved input can be lost, so press Home to just leave it.

Instructions

Force-quit an app, like swiping it away in the app switcher.

Use it to reset an app to a fresh start or to stop something running. Unsaved input in that app (for
example a half-written message) can be lost, so prefer iphone_press_button('home') to just leave it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "app": "<app>"
    },
    "name": "iphone_close_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesApp name as shown on the home screen (e.g. 'Settings', 'Einstellungen', 'Safari') or bundle ID (e.g. 'com.apple.Preferences').

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.0
    • addedInput schema / properties / app / description
      Added value: +"App name as shown on the home screen (e.g. 'Settings', 'Einstellungen', 'Safari') or bundle ID (e.g. 'com.apple.Preferences')."
    • addedInput schema / properties / app / minLength
      Added value: +1
  2. First observedv0.1.0

TDQS

A5/5.0
Behavior5/5

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

The annotations only say destructiveHint=true in the abstract, but the description specifies what is actually destroyed: unsaved input in the target app (for example a half-written message) can be lost. It also supplies the concrete call syntax for the safer alternative, so the risk and the way to avoid it are both actionable rather than generic.

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?

Two short sentences, zero waste. The definition is front-loaded: it gives the identity and analogy first, then the use cases, then the risk and the safer alternative. Each sentence does distinct work.

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?

Given a single documented parameter, existing annotations and a declared output schema, the definition covers everything an agent needs: what the tool does, when to use it, what can be lost, and what to call instead. Return values need not be explained because the output schema supplies them.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the single required parameter is documented there with format and examples (home-screen name or bundle ID). The description adds no parameter detail of its own, so the schema carries that load. A score of 3 is the correct baseline when the schema documents everything.

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 uses a specific verb and resource ("force-quit an app") and anchors it with a concrete analogy to swiping in the app switcher, which pins down the exact semantic (kill, not merely background). This clearly separates it from relatives such as launching or navigating away, so an agent can tell what it does 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states when to use it (reset an app to a fresh start, stop something running) and names an explicit alternative with the condition that selects it: prefer iphone_press_button('home') merely to leave the app. Both the when and the when-not are present, so there is nothing left to infer.

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