Skip to main content
Glama

Destroy a machine

destroy_vm
Destructive

DESTROYS the machine and its disk, with no undo and no backup kept. With when=now on a monthly or yearly machine: the unused paid time, less the hours used at the hourly rate, returns as account credit; the share paid with gifted credit returns as gifted credit. If the plan changed during the period or the expiry was changed by hand, support works out the amount. Ask the user first. confirm_hostname must be the machine's exact hostname. Scope: vms.destroy.

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": {
      "vm": "<vm>",
      "confirm_hostname": "<confirm_hostname>"
    },
    "name": "destroy_vm"
  }
}

Input Schema

NameRequiredDescriptionDefault
vmYesMachine id, as returned by list_vms or create_vm.
whenNoMonthly and yearly machines only: at the end of the paid period (nothing returned), or now (the unused paid time, less the hours used at the hourly rate, returns as account credit; gifted credit returns as gifted; support works out the amount if the plan changed during the period or the expiry was changed by hand).
confirm_hostnameYesThe machine's exact hostname, typed back as confirmation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / when / description
      Previous value: -"Monthly machines only: at the end of the paid period (nothing returned), or now (the unused paid time, less the hours used at the hourly rate, returns as account credit; gifted credit returns as gifted; nothing for an annual plan; support works out the amount if the plan changed during the period or the expiry was changed by hand)."New value: +"Monthly and yearly machines only: at the end of the paid period (nothing returned), or now (the unused paid time, less the hours used at the hourly rate, returns as account credit; gifted credit returns as gifted; support works out the amount if the plan changed during the period or the expiry was changed by hand)."
  2. Changed1 schema field changed
    • changedInput schema / properties / when / description
      Previous value: -"Monthly machines only: at the end of the paid period, or now."New value: +"Monthly machines only: at the end of the paid period (nothing returned), or now (the unused paid time, less the hours used at the hourly rate, returns as account credit; gifted credit returns as gifted; nothing for an annual plan; support works out the amount if the plan changed during the period or the expiry was changed by hand)."
  3. First observed

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 readOnlyHint=false, and the description adds substance beyond that: 'no undo and no backup kept' clarifies the exact permanence, and the refund/credit accounting rules for when=now (unused paid time less hours used, gifted credit returning as gifted, support adjudication on plan changes) are behavioral detail unavailable anywhere in the schema. The 'Ask the user first' instruction and the scope token 'vms.destroy' add safety-relevant context.

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-loads the irreversible consequence in the first sentence, then the refund rules, then the confirmation requirement and scope. It is dense and every sentence carries information, though the refund accounting sentence is long and could be tightened; no filler is present.

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 tool with no output schema, the description covers the permanence, the financial outcome of each `when` branch, the confirmation requirement, the escalation case, and the scope. An agent has everything needed to warn the user and call it correctly.

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 nonetheless reinforces the critical semantics of confirm_hostname ('must be the machine's exact hostname') and fully explains the when enum's financial consequences, which the schema also states. It adds marginally beyond the schema rather than something new, so it lands slightly above 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?

The description opens with a specific verb and resource ('DESTROYS the machine and its disk'), states the irreversible consequence, and includes a scope token 'vms.destroy'. An agent can immediately tell this apart from sibling tools like get_vm or power_vm, which are non-destructive.

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 behavioral prerequisite ('Ask the user first') and a condition-based routing rule ('With when=now on a monthly or yearly machine...'). It doesn't explicitly name a non-destructive alternative for stopped/reboot scenarios, but the guidance is clear enough to act on.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.