Skip to main content
Glama
matt-coppinger

Horizon MCP Server

list_machines

Retrieve virtual desktops by filtering on pool or state, with pagination and sorting for VDI inventory management.

Instructions

List machines (virtual desktops) in the environment.

To filter by pool, use: filter={"type":"Equals","name":"desktop_pool_id","value":""} To filter by state, use: filter={"type":"Equals","name":"state","value":"AVAILABLE"}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number (1-based)
sizeNoResults per page (max 1000)
filterNoHorizon filter JSON string. Example: {"type":"Equals","name":"desktop_pool_id","value":"<pool-id>"}
sort_byNoField name to sort by, e.g. name
order_byNoSort direction: ASC or DESC

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose that this is a read-style list operation and shows the filtering behavior with concrete examples, but it does not mention pagination behavior, authentication requirements, or any side effects. This is adequate but leaves some behavioral context implicit.

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?

The description is compact and front-loaded: the purpose appears first, followed by two barely redundant, high-value filter examples. Every line earns its place and no fluff is present.

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?

Given the presence of an output schema and full parameter documentation, the description covers the essential call semantics: what the tool lists and how to filter the most common dimensions. Minor gaps remain around pagination defaults and any prerequisite authentication, but these are partially covered by the schema and the overall tool context.

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%, establishing a baseline of 3. The description adds meaningful value beyond the schema by giving two ready-to-use filter strings and a concrete valid state value ('AVAILABLE'), which helps the agent construct correct filter JSON without additional inference.

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?

The description states a specific verb and resource: 'List machines (virtual desktops) in the environment.' It also clarifies that 'machines' means virtual desktops, which distinguishes this from related list tools such as list_connection_servers or list_desktop_pools.

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?

The description provides clear and practical usage context by showing exactly how to filter by pool and by state. It does not explicitly exclude alternatives like get_machine, but the filter examples give an agent enough direction to use the tool correctly for common list scenarios.

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