Skip to main content
Glama
Sign In

ARADIA | sovereign agentic systems

by com.aradia
OverviewDiscussionsAdmin

query_hardware_specs

Read-only

[PURPOSE]: Retrieves physical compute specs, 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 hardware sizing, VRAM fit, and multi-agent capacity. [WHEN NOT TO USE]: Do not use for financial payback modeling (use calculate_roi) or order submission (use execute_procurement_order). [SIDE EFFECTS]: None (pure read-only query).

Input Schema

NameRequiredDescriptionDefault
tierNoTarget hardware platform tier. If omitted, returns all tiers.

Output Schema

NameRequiredDescriptionDefault
specsYesHardware specifications and VRAM limits per tier
pricingYesFlat-rate turnkey and SLA pricing

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / tier / description
      Previous value: -"Filter by specific hardware tier. Leave blank for full catalog."New value: +"Target hardware platform tier. If omitted, returns all tiers."
    • removedOutput schema / properties / message
      Removed value: -{
-  "description": "Operational notice",
-  "type": "string"
-}
  2. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the '[SIDE EFFECTS]: None (pure read-only query)' line largely restates structured data. It adds useful scoping context (this is a discovery-stage sizing query, not a mutation), but says nothing about latency, caching, or result shape beyond what the output schema covers. With annotations carrying the safety profile, a 3 is appropriate.

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?

Bracketed section labels front-load purpose, routing rules, and side effects in four short lines with zero filler. Optimal for scanning during tool selection.

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?

Output schema exists, so return-value explanation is unnecessary. Combined with perfect schema coverage and clear annotations, an agent has everything needed to select and invoke this tool correctly.

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% with a single enum-typed 'tier' parameter whose description already covers the omit-to-return-all-tiers behavior. The description adds no tier-specific guidance. Baseline 3 applies when the schema does the heavy lifting.

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 (Retrieves) and a precise resource (physical compute specs, VRAM limits, batching concurrency limits) scoped to Aradia DGX systems. Concrete figures (128GB Spark, 748GB Station, 1,440GB B200 Rack) let an agent immediately distinguish it from sibling tools.

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]' (initial discovery, sizing, VRAM fit, multi-agent capacity) and '[WHEN NOT TO USE]' that names the two alternatives and their conditions (calculate_roi for payback modeling, execute_procurement_order for ordering). Nothing is left to inference.

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

All ARADIA | sovereign agentic systems 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