Skip to main content
Glama

relaunch_app

Restart an iOS Simulator or Mac app so its network traffic routes through configured rules and requests are recorded; use after setting network rules on an app that was already running.

Instructions

Quit and reopen a simulator app with request monitoring, so every connection it makes goes through its rule and its requests are recorded. Do this after the first set_network for an app that was already running.

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>",
      "simulator": "<simulator>"
    },
    "name": "relaunch_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesThe app: a bundle ID like com.me.MyApp, an app name, or * for every app in a simulator.
simulatorYesFor iOS Simulator apps: booted, any, a device name or a UDID. Leave out for a Mac app.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
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 it does disclose the key consequence: the app is terminated and restarted, and afterwards its connections are filtered by its rule and its requests are recorded. It does not say whether in-flight state is lost or what happens to an app that is not currently running, which is the main remaining behavioral gap.

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 sentences, zero waste: the first establishes the action and its effect, the second establishes the prerequisite ordering. The most decision-relevant information is front-loaded.

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 two-parameter tool with no output schema and no annotations, the description covers what it does, why (monitoring), and when to invoke it. A brief note on the post-restart state of the app or on where the recorded requests surface would make it fully self-sufficient.

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%, so bundle ID / name / '*' semantics and the simulator targeting options are already fully documented in the schema. The description adds nothing parameter-specific, so the baseline of 3 applies.

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 states a specific verb pair and resource ('Quit and reopen a simulator app') plus the distinguishing capability ('with request monitoring ... every connection it makes goes through its rule and its requests are recorded'). That clearly separates it from set_network, which configures rules, and from get_requests, which reads recorded traffic.

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 an explicit ordering condition: 'Do this after the first set_network for an app that was already running.' That tells the agent the prerequisite and the situation that calls for a relaunch. It stops short of naming when not to use it (e.g. for an app that was not already running, where a plain launch may suffice).

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