instabox-mcp

Get machine metrics

instabox_get_machine_metrics

Read-onlyIdempotent

Retrieves CPU and memory samples for a specified machine over a chosen time window, helping you monitor resource usage and diagnose performance issues.

Instructions

CPU and memory samples (one per 30 s, oldest first) measured on the host for a machine. Empty while the machine is not running; a new machine's first sample appears after ~90 s. Default window is the last 5 minutes, at most 24 h back.

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_metrics"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	Machine ID (m_...) or its unique name
`since`	No	RFC 3339 start of window, e.g. 2026-10-25T10:00:00Z

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 1, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds behavior the annotations cannot: 30 s sampling cadence, oldest-first ordering, empty-while-stopped meaning, a ~90 s warm-up for new machines, and a hard 24 h lookback limit. Those are exactly the details that prevent misinterpretation of an empty or short result set.

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 sentences, each carrying non-redundant information, with the output identity front-loaded and constraints following. Nothing here is filler or restatement of 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 does the minimum needed by describing cadence and ordering of returned samples, plus boundary behavior. It could go slightly further on the sample record shape (which metric fields are present), but an agent has enough to call and interpret 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 description coverage is 100%, so `id` and `since` are already documented. The description adds semantics the schema lacks entirely: the default window when `since` is omitted and the maximum backwards extent, which directly affects how an agent should set the parameter.

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?

The description clearly states the resource (CPU and memory samples) and its scope ('measured on the host for a machine'), which distinguishes it in practice from the sibling instabox_get_machine_usage. It never names that sibling explicitly, so the differentiation is implicit rather than spelled out.

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 supplies real decision context: the default 5-minute window, the 24 h retrieval ceiling, and the fact that results are empty while a machine isn't running, so an agent knows when this call is and isn't useful. It stops short of naming alternatives such as instabox_get_machine_usage for billing-style data.

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