Etuki FinOps & LLM Pricing Oracle

pin_single_model_prefix_cache

Read-onlyIdempotent

Projects 10-turn session caching costs for a target model under Case A (100% static prefix) and Case B (90% static prefix + 10% dynamic tail) and outputs provider cache-control templates. In-memory actuarial lookup requiring no API keys; unknown model IDs default to 'openai/gpt-6.1-sol' and prompts under 1,024 tokens bypass warm discounts. Resolves model's warm multiplier (0.05x-0.25x) from the UMCE registry to return provider_cache_protocol_mechanism, ten_turn_cost_comparison_on_same_model, and two_vector_actuarial_reference_table (benchmarking 150K and 200K token reference vectors). Use this tool to quantify 10-turn caching ROI on a specific model; use optimize_prompt_cache_layout instead when fixing mid-prompt token ordering.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pin_single_model_prefix_cache"
  }
}

Input Schema

Name	Required	Description	Default
`model`	No	Target LLM model ID ('vendor/model-slug', e.g. 'openai/gpt-6.1-sol' or 'openai/gpt-4.1').	openai/gpt-6.1-sol
`prompt_tokens`	No	Input prompt token count per turn (>= 1024 cacheable threshold).

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 9, 2026

changedInput schema / properties / model / description

Previous value: -"Target LLM model ID (e.g. 'openai/gpt-6.1-sol' or 'openai/gpt-4.1')."New value: +"Target LLM model ID ('vendor/model-slug', e.g. 'openai/gpt-6.1-sol' or 'openai/gpt-4.1')."

changedInput schema / properties / prompt_tokens / description

Previous value: -"Input prompt token count per turn (e.g. 150000 or 200000)."New value: +"Input prompt token count per turn (>= 1024 cacheable threshold)."

addedInput schema / properties / prompt_tokens / minimum
```
Added value: +1024
```

Changed2 schema fields changedNov 9, 2026

changedInput schema / properties / model / description

Previous value: -"Target model ID"New value: +"Target LLM model ID (e.g. 'openai/gpt-6.1-sol' or 'openai/gpt-4.1')."

changedInput schema / properties / prompt_tokens / description

Previous value: -"Prompt token count"New value: +"Input prompt token count per turn (e.g. 150000 or 200000)."

Changed2 schema fields changedNov 9, 2026
- addedInput schema / properties / model / description
```
Added value: +"Target model ID"
```
- addedInput schema / properties / prompt_tokens / description
```
Added value: +"Prompt token count"
```
AddedNov 8, 2026
RemovedNov 7, 2026
AddedNov 6, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/closed-world safety, and the description adds substantive context beyond them: in-memory actuarial lookup, no API keys required, unknown model IDs falling back to a default, and sub-1,024-token prompts bypassing warm discounts. These are real behavioral quirks an agent would otherwise miss; only return-value shape detail is thin.

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?

Purpose and both cases are front-loaded, and usage guidance closes the paragraph, so structure is sound. It is jargon-dense (field names like two_vector_actuarial_reference_table inline) and could be split for scanability, but every sentence carries information.

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

Completeness5/5

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

For a two-parameter, read-only calculation tool with no output schema, the description covers inputs, defaults, edge-case thresholds, and names the three returned artifacts, so an agent knows what it gets back. Nothing needed to call it correctly is missing.

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 coverage is 100%, so baseline is 3, but the description adds meaning the schema lacks: it clarifies that the model default also applies to unrecognized IDs, and that prompt_tokens below 1,024 changes behavior rather than merely being invalid. That is meaningful semantics beyond the field descriptions.

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?

States a specific verb and resource — projecting 10-turn session caching costs for a target model under Case A (100% static prefix) and Case B (90% static prefix + 10% dynamic tail) — and names the sibling it is not (optimize_prompt_cache_layout). An agent can distinguish it from cost/layout siblings without opening the schema.

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

Usage Guidelines5/5

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

Explicitly says when to use it ('quantify 10-turn caching ROI on a specific model') and names the alternative plus the selecting condition ('fixing mid-prompt token ordering' → optimize_prompt_cache_layout). Nothing is left to inference.

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

All Etuki FinOps & LLM Pricing Oracle tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.