Skip to main content
Glama
hcloud-mcp
by Xodus-CO

rebuild_server

Destructive

Reinstall a server from a specified image, wiping all disk data while keeping its ID and IPs; optionally override cloud-init user data. Irreversible, so confirm before use.

Instructions

Reinstall a server from an image, WIPING ALL DATA on its disk (attached volumes are kept). The server keeps its ID and IPs. Optional user_data (cloud-init) overrides the original. Returns an Action and, for images that use one, a new root_password. Irreversible; confirm with the user first

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": {
      "id": "<id>",
      "image": "<image>"
    },
    "name": "rebuild_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesServer ID
imageYesImage name or ID, e.g. ubuntu-24.04 (check list_images deprecation)
user_dataNoCloud-Init user data (max 32KiB)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A4/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: the destructive scope is precisely bounded (all disk data wiped, attached volumes kept), identity is preserved (ID and IPs unchanged), and the return payload is disclosed (Action plus a possible new root_password). Annotations already flag destructiveHint=true, and the description reinforces rather than contradicts it, though it does not cover auth/permission requirements or how the action can be tracked to completion.

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?

Four short sentences, front-loaded with the destructive consequence, then identity retention, then optional-parameter behavior, then the safety instruction. No filler, and the most consequential fact comes first.

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?

For a three-parameter destructive mutation with no output schema, the description covers everything an agent needs: what is destroyed, what survives, what the server retains, what the optional parameter overrides, and what comes back (Action and root_password). Nothing material 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?

With 100% schema coverage the baseline is 3, and the description earns an upgrade by explaining the semantic effect of user_data (it overrides the image's original cloud-init data) rather than just restating the field. It does not elaborate on the image parameter, but the schema already carries an example and a pointer to list_images.

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 verb+resource combination: "Reinstall a server from an image," and adds scope detail (wipes disk, keeps volumes, retains ID and IPs). It is clearly differentiable from reboot_server/reset_server in practice, though it never names an alternative to contrast with.

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?

Gives a strong precondition ("Irreversible; confirm with the user first") and clarifies that user_data overrides the original, but offers no explicit when-to-use vs. when-not guidance or comparison to siblings like reset_server or create_server (which would rebuild from scratch).

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

Deploy Server

Other Tools