Model Ruler — AI Cost Calculators

Fine-Tune ROI Calculator

fine-tune-roi-calculator

Read-onlyIdempotent

Use when a user is considering fine-tuning vs prompt engineering. Returns training cost, monthly inference savings, months-to-ROI, and breakeven volume.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "train_tokens": 50000000,
      "monthly_inference_tokens": 300000000
    },
    "name": "fine-tune-roi-calculator"
  }
}

Input Schema

Name	Required	Description
`train_tokens`	Yes	Training tokens (dataset × epochs)
`train_cost_per_1m`	No	Training cost per 1M tokens
`prompt_reduction_pct`	No	Prompt size reduction % from eliminating few-shot (default 0)
`base_inference_cost_1m`	No	Baseline API output cost per 1M
`monthly_inference_tokens`	Yes	Expected monthly inference volume (output tokens)
`finetuned_inference_cost_1m`	No	Fine-tuned inference cost per 1M

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 6, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds the return-value set (ROI, breakeven volume), which is useful given no output schema, but says nothing about assumptions, defaults, or how optional inputs behave.

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?

Two sentences, zero filler. The usage condition is front-loaded and the output list follows immediately, so an agent can skim it in one pass.

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?

With no output schema, the description usefully enumerates the four returned values, which is the key missing structured information. It is still silent on defaults for optional inputs (e.g. prompt_reduction_pct default 0) and on how missing cost parameters are resolved.

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 six parameters, each documented with units and role, so the schema carries the semantic load. The description adds no parameter-level detail beyond that, which is the expected baseline when the schema is complete.

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 decision ('fine-tuning vs prompt engineering') and enumerates the concrete outputs (training cost, monthly inference savings, months-to-ROI, breakeven volume), so the agent knows exactly what the tool produces. It does not differentiate itself from the many sibling *-calculator tools, which is the main gap.

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?

'Use when a user is considering fine-tuning vs prompt engineering' is an explicit usage trigger tied to a user intent. There is no guidance on when to prefer the sibling tools (e.g. provider-cost-calculator or agent-loop-cost-calculator) or when not to use this one.

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

All Model Ruler — AI Cost Calculators tools Inspect

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

Need Help?