Skip to main content
Glama

readygpu: hardware for local AI

Find graphics cards or machines

find_hardware
Read-onlyIdempotent

List graphics cards or complete machines (Macs, mini PCs) sold in a market, with memory, bandwidth, the estimated speed on a model and a link to each one's page and prices. Filter by minimum memory and new or used; sort by speed or popularity.

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": "find_hardware"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNogpu_card
sortNospeed
limitNo
modelNoA model slug (from search_models) for the speed column; a reference model by default
marketNoWhich market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada).us
contextNoContext length in tokens: 8192, 32768, 65536 or 131072.
conditionNoany
min_memory_gbNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"Where to price it: us, uk, de (Germany and the rest of the EU) or ca (Canada)."New value: +"Which market's catalogue: us, uk, de (Germany and the rest of the EU) or ca (Canada)."
    • removedInput schema / properties / max_price
      Removed value: -{
      -  "description": "Highest price, in whole units of the market's currency",
      -  "exclusiveMinimum": 0,
      -  "type": "number"
      -}
    • changedInput schema / properties / sort / enum
      Previous value: -[
      -  "speed",
      -  "price",
      -  "value",
      -  "price_per_gb",
      -  "popularity"
      -]New value: +[
      +  "speed",
      +  "popularity"
      +]
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description usefully adds what comes back per item (memory, bandwidth, estimated speed against a model, page link, prices) in the absence of an output schema. It says nothing about catalogue size, freshness, result caps (limit max 30) or what 'estimated' speed implies, which are the remaining behavioural gaps.

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?

Two sentences, no filler, with the resource and returned fields front-loaded before the filter/sort clause. Dense but readable; every clause carries an actual parameter or return-value detail.

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 an 8-param, all-optional listing tool with no output schema, the description covers what the tool returns and which filters matter, which is the critical missing piece elsewhere. The main shortfall is the absent guidance on when to prefer this over the sibling tools that also surface hardware (best_hardware, hardware_for_model, compare_hardware).

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?

With only 38% schema description coverage across 8 params, the description compensates for some of the undocumented ones: kind (cards vs machines), condition (new/used), and min_memory_gb filtering are all named in prose. But 'sort by speed or popularity' merely restates the enum, and limit plus the context-length parameter get no explanation beyond the schema. Useful but partial coverage.

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?

Clear verb (list) plus a specific resource split into two kinds (gpu cards, complete machines) with concrete examples (Macs, mini PCs). It concisely names the returned fields (memory, bandwidth, estimated speed, links, prices). It does not explicitly differentiate itself from siblings like best_hardware or hardware_details, so it stops short of a 5.

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 through the filter/sort sentence ('Filter by minimum memory and new or used; sort by speed or popularity'), which describes options rather than when to choose this tool over best_hardware, compare_hardware or hardware_for_model. The only cross-tool routing hint is 'a model slug (from search_models)', which is a pipeline note, not an alternative-selection rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources