Horizon MCP Server

reset_or_restart_sessions

Destructive

Power-cycle or reboot the VM backing a session to recover from unresponsive states, ending the user's session. Use reset for a hard cycle (may cause data loss) or restart for a graceful reboot.

Instructions

Reset or restart the virtual machine backing one or more sessions.

CAUTION: Both actions will terminate the user's session. reset is a hard power-cycle and may cause data loss. restart attempts a graceful reboot but the session will still end. Always confirm with the user before calling this.

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes	reset: hard power-cycle the VM (immediate, may cause data loss). restart: graceful reboot of the VM (user is logged off first).
`confirm`	No	Only used when the server runs with HORIZON_CONFIRMATION=flag (clients without elicitation). Otherwise the user is asked to confirm directly in the client.
`session_ids`	Yes	List of session IDs to act on

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.2.0Sep 30, 2026

addedInput schema / properties / confirm

Added value: +{
+  "default": false,
+  "description": "Only used when the server runs with HORIZON_CONFIRMATION=flag (clients without elicitation). Otherwise the user is asked to confirm directly in the client.",
+  "type": "boolean"
+}

First observedv0.1.0Sep 10, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and non-idempotent, and the description adds the crucial consequences: both actions terminate the session, reset may cause data loss, restart still ends the session even though it is graceful. This is exactly the extra consequence detail a destructive tool needs.

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?

Four short lines, each earning its place: purpose first, then the two per-action cautions, then the confirmation requirement. No filler or repetition.

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 destructive two-action tool with an output schema already present, the description covers impact, reversibility implications, and the confirmation prerequisite. Nothing an agent needs to call it safely 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 description coverage is 100%, including the action enum semantics and the confirm-flag behavior, so the schema already carries parameter meaning. The description reinforces reset-vs-restart but adds no syntax or values beyond what the schema provides; 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+resource ('Reset or restart the virtual machine backing one or more sessions') and immediately distinguishes the two modes operationally (hard power-cycle vs graceful reboot). An agent can tell exactly what this does and how reset differs from restart without opening the schema.

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 clear when-to-use guidance for the two actions and a strong precondition ('Always confirm with the user before calling this'). It does not, however, route the agent against siblings like logoff_sessions, disconnect_sessions, or machine_action, which is the main gap.

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

Deploy Server