Skip to main content
Glama

get_boot_history

Read-onlyIdempotent

Lists recent boots newest first with boot/shutdown timings, failures, and shutdown reasons to diagnose slow starts, unexpected restarts, or crashes.

Instructions

Lists the machine's last boots, newest first, from the system's own logs. Each start in its steps: the firmware, the system's loader, Windows to the sign-in screen, the sign-in, and the sign-in to the desktop, with Group Policy's time and the slow sign-in steps (the time the sign-in screen waited for someone is apart). How the session before it ended: clean, a stop error (blue screen) with its code and dump, the power button held, or not shut down at all with when it was last seen running; who asked for a shutdown or restart (the program, as which user, the reason, its words: Windows Update, an installer, the user), how long shutting down took and how long the machine was off. What failed as it started (services that did not start or answer, drivers that did not load), and how the session went: how long it ran, its sleeps, the services that stopped unexpectedly. Where Windows keeps its own boot measurement it adds that and what it found slower than usual; on Linux, this boot's timings and slowest units from systemd. Use it when a PC starts slowly, restarted by itself or keeps crashing; list_startup_items lists what starts at sign-in. It only reads.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_boot_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many boots, newest first (1 to 60, default 15).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the closing "It only reads" earns no credit. The description does add real behavioral depth beyond annotations: it enumerates what each boot record contains (firmware/loader/OS phases, shutdown requester and reason, failed services and drivers, session sleep and runtime), which tells the agent what failures are diagnosable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and ordering are front-loaded, which is good, but the return-content inventory sprawls into long parenthetical chains ("the time the sign-in screen waited for someone is apart") that are hard to parse and bury the actionable information. The content is valuable but the phrasing is denser than needed.

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 carries the return-value burden and does so thoroughly across both Windows and Linux, plus failure diagnostics. Coverage is complete for the tool's complexity, though the dense enumeration could be structured more scannably.

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?

The single parameter is fully documented in the schema (100% coverage, including the 1–60 range and default 15). The description adds nothing about it, so the baseline 3 applies; it neither compensates nor detracts.

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 and resource plus scope: "Lists the machine's last boots, newest first, from the system's own logs." It also names a boundary against a sibling ("list_startup_items lists what starts at sign-in"), so an agent can separate boot-history retrieval from startup-item enumeration.

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 concrete trigger conditions — slow start, self-restart, repeated crashes — and points to list_startup_items as the adjacent alternative with a stated difference. No explicit exclusions or when-not cases are offered, which keeps it just short of a 5.

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