Skip to main content
Glama

GPU Finder

by dev.gpufinder
OverviewDiscussionsAdmin

Find the cheapest available GPU

get_market_snapshot
Read-only

Check a GPU configuration once or in a client-scheduled availability watch: cheapest listed and freshly observed in-stock offers for one GPU model and exact GPU count, with whole-node/per-GPU hourly USD price, observation time, provider and region. Optional provider and exact provider-reported region filters run before regional aggregation and are echoed in filters. Compare snapshots in client-owned state; ignore timestamp-only changes. The server does not schedule checks or send notifications. One data unit per call; get_usage is free. Stock is not a launch guarantee.

Input Schema

NameRequiredDescriptionDefault
gpuYesGPU model name, case-insensitive, e.g. "H100", "RTX 4090". See list_gpus.
countNoGPUs per node. Prices are for the whole node. Defaults to 1.
regionNoExact provider-reported region, case-insensitive (e.g. Japan or eu-north1). Obtain labels from get_prices. Not a broad Europe/Asia filter or a placement guarantee.
providerNoProvider name or slug, e.g. "runpod", "lambda". See list_providers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / provider
      Added value: +{
+  "description": "Provider name or slug, e.g. \"runpod\", \"lambda\". See list_providers.",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}
    • addedInput schema / properties / region
      Added value: +{
+  "description": "Exact provider-reported region, case-insensitive (e.g. Japan or eu-north1). Obtain labels from get_prices. Not a broad Europe/Asia filter or a placement guarantee.",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / count / description
      Added value: +"GPUs per node. Prices are for the whole node. Defaults to 1."
    • addedInput schema / properties / gpu / description
      Added value: +"GPU model name, case-insensitive, e.g. \"H100\", \"RTX 4090\". See list_gpus."
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: discloses billing semantics ('One data unit per call; get_usage is free'), that the server does not schedule checks or send notifications, that filters run before regional aggregation and are echoed in filters, and that stock is not a launch guarantee. These are exactly the behavioral facts an agent needs before invoking.

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-loads the core return content, then layers constraints and caveats in short clauses. Dense but virtually every sentence carries operational meaning; only the billing aside ('get_usage is free') is slightly tangential to 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?

No output schema exists, so the description must describe return content, and it does: per-GPU and whole-node hourly USD price, observation time, provider, region, and echoed filters. It also covers side effects, billing units, and stock caveats, leaving no obvious gap for correct invocation.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns an upgrade by clarifying that count is 'exact GPU count' with whole-node pricing and that provider/region filters are applied before regional aggregation and echoed back. It doesn't re-explain formats (case-insensitivity, label sources) that the schema already covers, which is appropriate.

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?

States a specific verb and resource: returns cheapest listed and freshly observed in-stock offers for one GPU model and exact GPU count, along with price, timestamp, provider and region. An agent can tell it apart from get_prices/get_availability in broad terms, though the description never explicitly names which sibling to use for related needs (e.g., historical or broad price listing).

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?

Clearly frames the usage pattern: 'Check a GPU configuration once or in a client-scheduled availability watch,' and explains client-owned comparison state, ignoring timestamp-only changes, and that the server does not schedule or notify. Missing explicit when-not or alternative-tool routing against get_availability and get_prices, which keeps it from a 5.

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

All GPU Finder toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources