Skip to main content
Glama

Delete a Machine and Stop Its Billing

varity_machines_delete
DestructiveIdempotent

Delete a Varity CPU or GPU virtual machine by ID, then wait up to 10 minutes for its billing to stop.

Instructions

Delete a Varity CPU or GPU virtual machine by id and wait (up to 10 minutes) until its billing reads stopped.

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": {
      "machine_id": "<machine_id>"
    },
    "name": "varity_machines_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
machine_idYesThe machine id from varity_machines_list.
idempotency_keyNoReuse the same key to retry a delete safely.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructive=true and idempotent=true, so the safety profile is covered. The description adds real context beyond them: the call blocks and waits up to 10 minutes, and success is defined as billing reading 'stopped'. It stops short of saying what happens on timeout or whether the VM is gone before billing settles.

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?

One sentence, front-loaded with the action and target, then the blocking behavior. No redundant restatement of the title or name.

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?

For a destructive mutation with no output schema, the definition covers the key operational fact an agent needs: the up-to-10-minute wait and the billing-stopped completion criterion. Minor gaps remain around timeout behavior and whether attached resources are affected, but nothing essential to invoking it is missing.

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

Parameters3/5

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

Schema coverage is 100%, with machine_id already documented as coming from varity_machines_list and idempotency_key documented for safe retries. The description only echoes 'by id' and adds no new semantics, so the baseline 3 applies.

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?

States a specific verb (delete) and resource (Varity CPU or GPU virtual machine) with the selector (by id), plus the completion condition (billing reads stopped). It is clearly distinct from varity_machines_create and varity_machines_list.

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?

Usage is only implied: an agent infers it should call this when a machine should be removed and billing terminated. There is no explicit when-not guidance (e.g., prefer stopping vs deleting, or handling machines that are mid-deploy), and no named alternative.

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