instabox-mcp

Delete a machine

instabox_delete_machine

Destructive

Permanently delete a machine and its disks while keeping saved snapshots; require the exact machine ID or name as confirmation to prevent deleting the wrong machine.

Instructions

PERMANENTLY delete a machine and its disks (snapshots saved from it are kept). Cannot be undone. To guard against deleting the wrong machine, confirm must be the machine's exact ID or name; the server rejects anything else with 409 delete_confirmation_required. Needs the machines:delete scope.

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>",
      "confirm": "<confirm>"
    },
    "name": "instabox_delete_machine"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Machine ID (m_...) or its unique name
`wait`	No	Wait for the operation to finish before returning (default true)
`confirm`	Yes	The machine's exact ID or name, repeated to confirm
`waitTimeoutSeconds`	No	Max seconds to wait (default 300)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 1, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, yet the description adds substantial non-redundant detail: disks are destroyed, snapshots survive, the action is irreversible, the required OAuth scope (machines:delete), and the exact 409 delete_confirmation_required rejection. That is exactly the behavioral context an agent needs before a destructive call.

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?

Three tight sentences, front-loaded with the irreversible outcome, then the safety mechanism, then the permission requirement. No filler and no repetition of schema content.

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?

Covers destruction scope, irreversibility, confirmation mechanics, error code, and auth scope, with no output schema to explain. It omits any mention of the asynchronous operation model implied by `wait`/`waitTimeoutSeconds` and the instabox_get_operation sibling, which is the one notable gap for a long-running destructive call.

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 baseline is 3; the description earns a step up by explaining the server-side contract for `confirm` (exact ID or name, otherwise 409 delete_confirmation_required) rather than just restating the field. `wait` and `waitTimeoutSeconds` are left entirely to the schema, which is acceptable given full coverage.

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 a specific verb and resource ('PERMANENTLY delete a machine and its disks') and immediately scopes the effect ('snapshots saved from it are kept'), which separates it cleanly from instabox_delete_snapshot and the other siblings. An agent knows exactly what this tool does without touching 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 Guidelines4/5

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

Gives a clear destructive-operation context ('Cannot be undone') and a concrete safety protocol for the confirm parameter, including the failure mode. It stops short of explicit routing guidance such as whether the machine must be powered off first or when to prefer instabox_update_machine instead, so it informs but doesn't fully disambiguate usage.

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