Skip to main content
Glama

OmniToolCalc LLM Token & Cloud FinOps Suite

estimate_llm_token_cost

Estimate 30-day enterprise LLM API spend and prompt-caching savings across GPT-5, Claude 4.5 Sonnet, Gemini 2.5 Pro, OpenAI o3, DeepSeek V3.2, and Gemini 2.5 Flash.

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": {
      "model": "<model>"
    },
    "name": "estimate_llm_token_cost"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesModel ID: gpt-5, claude-4-5-sonnet, gemini-2-5-pro, openai-o3, deepseek-v3-2, or gemini-2-5-flash
input_tokensNoAverage input tokens per request (default 8000)
output_tokensNoAverage output tokens per request (default 800)
cache_hit_ratioNoPrompt cache hit ratio from 0 to 1 (default 0.75)
requests_per_dayNoDaily API requests (default 10000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden. It discloses the 30-day projection horizon and that prompt-caching savings are included, but says nothing about whether this is a pure side-effect-free calculation, what pricing assumptions or list prices underlie the numbers, or how the result is broken down (per model vs. aggregate).

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?

A single front-loaded sentence with the verb and outcome first. The six-model enumeration is somewhat list-heavy but earns its place by telling the agent which models are valid inputs, though the schema already covers those IDs.

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?

For a pure estimation tool with no annotations and no output schema, an agent still lacks any sense of the return shape (a single monthly figure? a per-request breakdown? a savings delta?) and of the assumptions driving the estimate. The description is sufficient to know what the tool computes but not what comes back.

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 every parameter including defaults (8000 input tokens, 800 output, 0.75 cache ratio, 10000 requests/day) is already documented. The description adds only one piece of meaning the schema lacks: that requests_per_day is extrapolated over a 30-day window, which ties the parameters to the stated horizon. That is a marginal gain over baseline.

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?

Names a specific verb ('Estimate') and a specific resource ('30-day enterprise LLM API spend and prompt-caching savings'), plus enumerates the six supported models so the agent knows the scope. It does not distinguish itself from the sibling list_quantitative_calculators, but the verb+resource pairing is unambiguous on its own.

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 '30-day enterprise LLM API spend' framing implies the use case (cost projection before committing to a model), but there is no explicit when-to-use statement, no when-not-to-use, and no pointer to alternatives such as list_quantitative_calculators or any per-request pricing tool.

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