RCF MCP Server

Overview Schema Source Related Servers Discussions Admin

compute.inspect_node

compute_inspect_node

Read-only

Probe a node read-only for CPU, memory, disk, GPUs, and Slurm partitions, and assess GPU schedulability using free VRAM as capacity, not availability.

Instructions

Probe a node read-only: CPU, memory, disk, GPUs and Slurm partitions, plus an explicit GPU schedulability assessment (free VRAM is never treated as availability).

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": {
      "node_id": "<node_id>"
    },
    "name": "compute_inspect_node"
  }
}

Input Schema

Name	Required	Description	Default
`node_id`	Yes
`refresh`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered, but the description adds genuinely non-obvious behavior: it performs an explicit GPU schedulability assessment and deliberately does not equate free VRAM with availability. That prevents a real misinterpretation of results. It stops short of covering caching/refresh behavior or result shape.

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?

A single front-loaded sentence with no filler: verb first, then the inspected dimensions, then the one non-obvious behavioral caveat. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

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 reasonably cover what the probe reports (CPU, memory, disk, GPUs, partitions, schedulability). However, for a two-parameter tool with zero schema documentation, leaving 'refresh' undefined is a real gap an agent could trip over.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, yet it never mentions either parameter. 'node_id' is guessable from context, but 'refresh' (default false) is completely unexplained — the agent cannot tell whether it forces a live probe, bypasses a cache, or changes cost/latency.

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 opens with a specific verb and resource ('Probe a node read-only') and enumerates exactly what is inspected: CPU, memory, disk, GPUs, Slurm partitions, plus a GPU schedulability verdict. That makes it distinguishable from compute_list_nodes (list-level) and compute_node_selftest, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: it is clearly the single-node diagnostic counterpart to compute_list_nodes, and the read-only probe framing tells the agent it is a safe inspection step. There is no explicit when-to-use guidance, no exclusion against compute_node_selftest, and no explanation of when to pass refresh.

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