instabox-mcp

Get machine usage

instabox_get_machine_usage

Read-onlyIdempotent

Retrieve a machine's running, vCPU, memory, and disk usage over a chosen window for billing or cost checks, including deleted machines by ID.

Instructions

Resource usage of one machine over a window (running seconds, vCPU-seconds, GiB-seconds of memory and disk), for billing or cost checks. Defaults to the current UTC month; the window may span at most 366 days. Works for deleted machines too (by ID).

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>"
    },
    "name": "instabox_get_machine_usage"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Machine ID (m_...) or its unique name
`to`	No	RFC 3339 window end (default: now)
`from`	No	RFC 3339 window start (default: start of this UTC month)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 1, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so safety is covered. The description adds genuine behavioral context beyond them: default window behavior, the 366-day hard ceiling that will cause failures on wide ranges, and that deleted machines remain retrievable — a non-obvious trait for a read tool.

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 short sentences, front-loaded with what is returned and why, then defaults and limits. Every clause carries information an agent could act on; nothing is redundant with the title.

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?

With no output schema, the description usefully names the returned measurements, which is the main thing an agent needs to interpret results. It could go slightly further on whether values are aggregated per window or broken down over time, and on whose scope usage is billed, but the essentials are present.

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% and the schema already documents id, from and to with RFC 3339 formats and defaults. The description corroborates the default window (current UTC month) but adds no new per-parameter detail beyond the 366-day span limit, which is a cross-parameter constraint rather than parameter semantics. Baseline 3 applies.

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 resource (resource usage of one machine) and enumerates the measured quantities (running seconds, vCPU-seconds, GiB-seconds of memory and disk), which implicitly separates it from the org-level instabox_get_usage and the performance-oriented instabox_get_machine_metrics. It stops short of naming those siblings, so the differentiation is inferable rather than explicit.

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 use case (billing or cost checks) plus the operational guardrails an agent needs: the window defaults to the current UTC month and may span at most 366 days, and deleted machines can still be queried by ID. No explicit 'use X instead' routing to instabox_get_usage or instabox_get_machine_metrics, so alternatives are left to inference.

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