llm-price-mcp

compare_cost

Estimate and rank the USD cost of a token-based workload across multiple LLM models, ordered cheapest first, so you can choose budget-friendly options.

Instructions

Estimate and rank the cost (USD) of a workload across several models, cheapest first.

Args: models: Model ids such as "openai/gpt-4o-mini" (a unique substring also works). input_tokens: Number of prompt/input tokens. output_tokens: Number of completion/output tokens.

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": {
      "models": "<models>",
      "input_tokens": "<input_tokens>",
      "output_tokens": "<output_tokens>"
    },
    "name": "compare_cost"
  }
}

Input Schema

Name	Required	Description	Default
`models`	Yes
`input_tokens`	Yes
`output_tokens`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 3, 2026

TDQS

A3.6/5.0

Behavior3/5

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

No annotations exist, so the description carries the full burden; it does disclose the currency (USD), the sorted output order, and that a unique substring of a model id is accepted. It does not say what happens with an unknown or ambiguous model id, whether pricing is static or fetched live, or whether failures abort the whole comparison.

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?

The behavior statement is front-loaded in one sentence, followed by a compact Args block that earns its space by adding format and matching details absent from the schema. Minor redundancy in restating what the token parameters mean, but nothing is wasteful.

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 an output schema present, return-value explanation is unnecessary, and all three required parameters are covered in the description. What remains missing is edge-case behavior for invalid or ambiguous model ids and whether the estimate reflects current pricing, which are the main residual gaps for a 3-parameter comparison tool.

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 description coverage is 0%, so the description must compensate, and it largely does: it documents all three parameters and adds meaning the schema lacks, including the model id format ('openai/gpt-4o-mini') and the substring-matching shortcut, plus the prompt-versus-completion distinction for the token counts.

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 first sentence gives a specific verb pair (estimate and rank) plus the resource (workload cost in USD across models) and the ordering guarantee (cheapest first). It is clearly distinguishable from list_models, gpu_rental_prices, and estimate_self_host, though it never addresses the closely named sibling 'cheapest', leaving that boundary implicit.

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: 'across several models' suggests multi-model comparison, but there is no explicit when-to-use versus 'cheapest' or 'estimate_self_host', nor any stated precondition such as needing known token counts. An agent must infer the selection rule from the description alone.

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

Deploy Server