Skip to main content
Glama

Estimate what runs cost

estimate_cost
Read-only

What Federated Computing runs cost in confidential cloud time, at Google Cloud list prices, for the machines and run times the real runs used, plus key services. Same numbers as the cost estimator page. An estimate, not a quote.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>"
    },
    "name": "estimate_cost"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYestabular-cpu (credit, fraud, risk models), tabular-tdx, gpu-small, or gpu-llm-14b.
runsNoHow many runs. Default 1.
monthsNoMonths the key services stay up. Default 3.
key_servicesNoKey services, one per data or model owner. Default 2.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "tabular-cpu",
      -  "tabular-tdx",
      -  "gpu-small",
      -  "gpu-llm-14b"
      -]New value: +[
      +  "tabular-cpu",
      +  "tabular-tdx",
      +  "gpu-small",
      +  "gpu-llm-14b",
      +  "gpu-llm-72b"
      +]
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful context beyond that: the pricing basis (Google Cloud list prices, confidential cloud time) and the caveat 'An estimate, not a quote,' which sets expectations about precision. It does not describe the shape of the returned figures or what is itemized.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, which is good, but the opening sentence is overstuffed and hard to parse ('for the machines and run times the real runs used'). The closing 'An estimate, not a quote' earns its place; the middle sentence about the estimator page is borderline filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should say something about what comes back (e.g., a per-line-item breakdown or a total), and it does not. It is otherwise adequate for a simple read-only four-parameter estimation tool with fully documented parameters.

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% and the enum for kind is documented inline, so the schema carries the parameter burden. The description mentions 'key services' and 'run times' in passing but adds no meaning beyond the schema's own definitions and defaults.

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?

The description names a specific verb (estimate cost) and a clearly bounded resource (Federated Computing runs in confidential cloud time, priced at Google Cloud list rates, including key services). No sibling tool overlaps this purpose, so it is effectively distinct, but the phrasing 'for the machines and run times the real runs used' is awkward and slightly obscures the scope.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives; the only contextual cue is 'Same numbers as the cost estimator page,' which tells the agent where the figures come from, not when to call the tool. The agent must infer that this is for pre-run cost projections.

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