Skip to main content
Glama
Sign In

Runcrate

by io.github.aeonmindai
OverviewDiscussionsAdmin

List GPU clusters

list_clusters
Read-onlyIdempotent

List the GPU clusters in the environment, newest first: id, name, status (provisioning, installing, ready, degraded, terminating, terminated, failed), node_count machines of gpus_per_node x gpu_type, location, interconnect, stack (none, slurm, kubernetes or ray), hourly_rate for the whole cluster and hourly_rate_per_node for one machine. Active clusters only unless status is all. A cluster's nodes are not in list_instances; get_cluster lists them.

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": "list_clusters"
  }
}

Input Schema

NameRequiredDescriptionDefault
statusNoactive (default): not terminated or failed. all: every cluster
workspaceNoWorkspace ID (optional: defaults to the authenticated workspace)
environmentNoEnvironment name (optional: defaults to the environment this session acts in)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish the read-only, idempotent, non-destructive, closed-world profile, and the description adds ordering (newest first), default filtering behavior, the full lifecycle status vocabulary, and a non-obvious cross-tool caveat that cluster nodes are absent from list_instances. These are genuine behavioral facts not present in the annotations. Pagination or limits, if any, are not mentioned.

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

Conciseness4/5

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

Front-loaded with the action and ordering, followed by the returned-field list and then the scoping and sibling caveats. The field enumeration is long but earns its place because there is no output schema. Slightly dense as a single compound sentence, but no filler.

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?

With no output schema, the description supplies the return shape itself (id, name, status, node_count, gpus_per_node, gpu_type, location, interconnect, stack, hourly_rate, hourly_rate_per_node), covers defaults for all optional parameters, and closes the loop on where node data lives. Nothing an agent needs to call this correctly 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%, and each parameter already documents its default and enum meaning, so the baseline is 3. The description reinforces the status default ('Active clusters only unless status is all') but adds no syntax or format detail for workspace or environment beyond what the schema states.

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 ('List the GPU clusters in the environment') plus ordering ('newest first') and enumerates the exact fields returned. It is immediately distinguishable from get_cluster (single cluster) and list_instances (machines), which the description explicitly addresses.

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 the default scoping rule ('Active clusters only unless status is all') and routes the agent to get_cluster when node-level detail is needed, plus warns that cluster nodes are not in list_instances. It does not spell out a full when-to-use/when-not statement, but the routing to alternatives is explicit enough to select correctly.

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

All Runcrate toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources