aradia-mcp-server

Official

Overview Schema Source Related Servers Discussions Admin

query_hardware_specs

Read-only

Retrieve verified physical compute specs, VRAM limits, and continuous batching concurrency limits for Aradia DGX systems to evaluate hardware sizing and multi-agent capacity.

Instructions

[PURPOSE]: Retrieves verified physical compute specifications, VRAM limits (128GB GB10 (Spark), 748GB GB300 (Station), 1,440GB B200 Rack), and continuous batching concurrency limits for Aradia DGX systems. [WHEN TO USE]: Call during initial discovery to evaluate physical hardware sizing, VRAM budget, and multi-agent capacity. [WHEN NOT TO USE]: Do not use for CapEx token financial payback modeling (use calculate_roi) or order submission (use execute_procurement_order). [SIDE EFFECTS & BEHAVIOR]: Pure read-only query. Generates zero external network side effects and incurs zero costs.

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": "query_hardware_specs"
  }
}

Input Schema

Name	Required	Description	Default
`tier`	No	Target hardware platform tier to inspect: 'spark' (5 users, 128GB VRAM), 'station' (50 users, 192GB VRAM), or 'b200' (500 users, 1536GB VRAM). If omitted, returns full catalog across all tiers.

Output Schema

Name	Required	Description	Default
`specs`	Yes	Physical compute specs, VRAM limits, and hardware interconnects per tier.
`pricing`	Yes	Flat-rate turnkey appliance pricing and monthly SLA rates.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.1.1Sep 13, 2026

addedInput schema / properties / tier / description

Added value: +"Target hardware platform tier to inspect: 'spark' (5 users, 128GB VRAM), 'station' (50 users, 192GB VRAM), or 'b200' (500 users, 1536GB VRAM). If omitted, returns full catalog across all tiers."

addedInput schema / properties / tier / enum

Added value: +[
+  "spark",
+  "station",
+  "b200"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "pricing": {
+      "description": "Flat-rate turnkey appliance pricing and monthly SLA rates.",
+      "type": "object"
+    },
+    "specs": {
+      "description": "Physical compute specs, VRAM limits, and hardware interconnects per tier.",
+      "type": "object"
+    }
+  },
+  "required": [
+    "specs",
+    "pricing"
+  ],
+  "type": "object"
+}

First observedv0.1.0Sep 13, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description still adds value by stating "zero external network side effects and incurs zero costs," which is behavior an agent cannot infer from the hints alone. It does not cover any auth requirement or output shape, but with an output schema present that is a minor gap.

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?

Labeled sections ([PURPOSE], [WHEN TO USE], [WHEN NOT TO USE], [SIDE EFFECTS]) make it scannable and front-load the verb and resource. The spec list in the purpose sentence is dense but each item is meaningful; no filler sentences beyond the partly redundant "pure read-only query" line.

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?

For a zero-required-parameter read tool with an output schema and full annotation coverage, the description supplies routing guidance, cost/network behavior, and usage phase — enough to call it correctly. The one substantive defect is the conflicting VRAM and user-capacity numbers, which undercut the stated purpose of capacity evaluation.

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 coverage is 100% for the single 'tier' parameter, so the baseline would be 3. However, the description's capacity figures conflict with the schema: it lists Station at 748GB and B200 at 1,440GB, while the schema enum describes Station as 192GB VRAM and b200 as 1536GB VRAM. An agent reasoning about sizing from the description would pick the wrong tier, which makes the added text actively misleading rather than merely redundant.

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?

A specific verb ("Retrieves") plus a concrete resource ("verified physical compute specifications, VRAM limits... and continuous batching concurrency limits") for a named product line. The scope is narrow enough that an agent can immediately tell it apart from financial modeling or ordering siblings.

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

Usage Guidelines5/5

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

Explicit [WHEN TO USE] names the phase ("initial discovery") and intent (hardware sizing, VRAM budget, multi-agent capacity). [WHEN NOT TO USE] names two concrete alternatives by tool name plus the condition that selects each (calculate_roi for payback modeling, execute_procurement_order for submission).

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

Deploy Server