FastGPU

Match a workload to the cheapest GPU

match_workload

Read-onlyIdempotent

The routing DECISION: describe a job (a model, size, or GPU need) and get the ranked, reasoned recommendation for the cheapest place to run it across the live market, with the required VRAM, GPU count, effective $/hr, and how much cheaper it is than a hyperscaler. No key required. Results mirror the site and apply a small, disclosed partner tie-break between otherwise-equal offers (each match reports partner true/false).

Input Schema

TableJSON Schema

Name	Required	Description
`spot`	No	Set true to include interruptible spot capacity for a cheaper rate.
`task`	No	What the job does.
`model`	No	Open model name to size against, e.g. "Llama 3 70B", "Qwen 72B", "Mixtral".
`query`	No	Plain-language job, e.g. "cheapest to serve Llama 3 70B" or "2x H100 for fine-tuning". Provide this OR a structured spec below.
`region`	No	Restrict to a data-residency region.
`vram_gb`	No	Rough VRAM the job needs, in GB, if you already know it.
`params_b`	No	Model size in billions of parameters when no exact model is named.
`reserved`	No	Set true to include reserved / committed-term capacity for a lower rate.
`gpu_count`	No	Force a specific GPU count instead of letting the engine size it.
`precision`	No	Numeric precision to size the model at.
`budget_usd_hr`	No	Only recommend configs at or under this hourly budget.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`hero`	No
`count`	Yes
`stale`	No
`matches`	Yes
`workload`	No
`updated_at`	No

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description goes beyond these by disclosing auth requirements ('No key required'), result provenance ('Results mirror the site'), and the crucial partner tie-break bias between otherwise-equal offers, including the partner true/false flag. This is exemplary transparent disclosure of a non-obvious behavior.

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?

The description is dense but every clause earns its place: the purpose, the returned fields, the auth note, the source mirroring, and the tie-break disclosure. It is front-loaded with 'routing DECISION' and structured so an agent can quickly extract intent and caveats.

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?

Given the tool's complexity (11 parameters, 5 enums, output schema present, annotations rich), the description covers the essential behavioral context: what it does, what it returns, auth, and the partner tie-break. The main gap is the absence of explicit routing guidance toward the sibling list_gpu_prices, which would make the decision space fully complete.

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%, so the schema already documents all 11 parameters thoroughly. The description adds no parameter-level details beyond mentioning 'a model, size, or GPU need' and the query-or-structured-spec pattern, which is also present in the query parameter description. Baseline 3 is appropriate.

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?

The description names a specific verb ('match'), a resource ('a workload to the cheapest GPU'), and a precise outcome ('ranked, reasoned recommendation' across the 'live market'). It clearly differentiates this from the sibling list_gpu_prices by framing it as a decision/routing tool rather than a price list, even without an explicit sibling mention.

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?

The description implies usage: the agent should call this when it has a job to route and wants a recommendation with VRAM, GPU count, and cost. However, it never explicitly references the sibling list_gpu_prices or states when to prefer raw price listing over this decision tool, leaving the alternative distinction to inference.

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

All FastGPU tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

The two tools have clearly distinct purposes: list_gpu_prices provides raw market data, while match_workload turns a workload description into a recommendation. There is no functional overlap between them.

Naming Consistency5/5

Both tool names follow the same verb_noun snake_case pattern: list_gpu_prices and match_workload. The naming is consistent, descriptive, and predictable.

Tool Count3/5

Two tools is on the thin side, but each tool earns its place for the server's narrow price-comparison and workload-matching purpose. The count feels minimal rather than excessive, so it lands in the borderline range.

Completeness5/5

For the stated purpose of comparing GPU prices and recommending the best match for a workload, the surface is complete: one tool exposes the live market, and the other provides the routed decision. No obvious dead ends or missing critical operations.

Resources

Need Help?