Skip to main content
Glama

Restart or stop the server

restart_server
Destructive

Schedule a Minecraft server restart or stop with chat countdown warnings, save all worlds and players, then disconnect everyone and shut down; cancel or check pending status.

Instructions

restart or stop after a countdown in chat: players see warnings at set marks, then every world and player is saved and the server shuts down. What runs the server decides what comes next: Docker's restart policy or a start script loop starts it again (and then a stop is a restart too); otherwise it stays off. One restart or stop is pending at a time, and scheduling replaces it; cancel calls it off, status tells whether one is pending. Needs server:control. Everyone online gets disconnected, so confirm with the user first.

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_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNo`status` reads the pending onerestart
messageNoSaid with each warning, such as the reason
countdownSecondsNo0 goes at once

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.2.1
    • addedInput schema / properties / action / description
      Added value: +"`status` reads the pending one"
    • addedInput schema / properties / countdownSeconds / description
      Added value: +"0 goes at once"
  2. First observedv4.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds substantive context beyond them: the countdown warning cadence, that all worlds and players are saved before shutdown, that scheduling replaces a pending operation, and the critical conditional that whether the server comes back depends on Docker's restart policy or a start-script loop. That last point materially changes how an agent should reason about 'stop'.

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?

Front-loaded with the primary verb and outcome, and every sentence carries information. It is somewhat dense and semicolon-chained, with the permission and confirmation notes buried at the end rather than surfaced earlier, which slightly hurts scanability.

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?

Covers what an agent needs for a destructive, no-output-schema mutation: what is destroyed (disconnects), what is preserved (saved worlds/players), whether it comes back up, concurrency rules, auth requirements, and a human-confirmation directive. Nothing essential 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?

Schema coverage is 100%, so the schema already documents `action`, `message`, and `countdownSeconds`. The description still adds meaning the schema does not: that a new schedule replaces a pending one (affecting the `restart`/`stop` enum values) and that `status` reads the pending operation rather than server health. Marginal but real added value over the baseline.

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?

Opens with the exact operations ('`restart` or `stop` after a countdown in chat') and spells out the mechanical consequence: warnings, full world/player save, shutdown. It also separates the non-destructive actions (`cancel`, `status`) from the destructive ones, so it is clearly distinguishable from siblings like get_server_status and save_worlds.

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?

Explicitly states when to use each action ('`cancel` calls it off, `status` tells whether one is pending'), names the permission prerequisite (needs server:control), and gives a directive to confirm with the user first because everyone online gets disconnected. Alternatives and the one-pending-at-a-time constraint are covered.

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