Skip to main content
Glama

Restart App

restart_app

Terminates and relaunches an application launched by this MCP session, preserving its original command, arguments, and working directory so you can recover or reset an active process.

Instructions

Gracefully terminates and re-launches an active process launched by this MCP session, preserving its original launch command, arguments, and working directory.

NOTE: Only applications launched by this MCP server can be restarted. External applications or user-opened windows cannot be restarted by the MCP server.

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": "restart_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
pidNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.4/5.0
Behavior3/5

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

The description adds real context beyond annotations: the operation is graceful, it restarts rather than a fresh launch, and it preserves launch command, arguments, and working directory. Annotations already declare a non-read-only, non-destructive, non-idempotent, closed-world profile, but the description is silent on the practical risk of a restart (in-memory state or unsaved work being lost) and on the state returned after restart, which for a process-killing operation is a notable omission.

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?

Two short sentences plus a clearly labelled NOTE, with the core behavior front-loaded and no filler. The parenthetical exclusion is well placed after the main definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so not explaining return values is acceptable, and the annotations carry the safety profile. However, for a restart tool the undefined optional pid and the missing note on state loss leave an agent without enough information to choose the right target and warn about consequences.

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

Parameters2/5

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

The single parameter pid is optional, is not required, and has 0% schema description coverage; the description never mentions it. An agent cannot tell from the definition what happens when pid is omitted (target the last launched app? a default window?) or what a pid belonging to an unmanaged process would do.

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?

States a specific compound verb (gracefully terminates and re-launches) plus the resource (a process launched by this MCP session) and notes that launch command, arguments, and working directory are preserved, which meaningfully separates it from a plain launch or terminate. It stops short of naming the sibling tools it sits between (launch_app, terminate_app), so differentiation is implied rather than explicit.

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?

The NOTE gives an explicit when-not condition: external applications or user-opened windows cannot be restarted, so an agent knows to reject those cases before calling. What is missing is a positive redirect (e.g. use terminate_app + launch_app for external processes), leaving the alternative route to inference.

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