Trust Engine MCP

estimate_switch_savings

Estimate monthly cost savings and quality tradeoffs when switching between measured AI model pairs using benchmark cost-per-solved-task data and your bill; other pairs get a free pilot.

Instructions

Use when asked "how much would we save by switching from model A to model B?". Works only for model pairs Trust Engine AI measured (Claude Opus, Sonnet, Haiku 5.5 on the Aider benchmark): returns the measured cost-per-solved-task ratio, the arithmetic on monthly_bill_usd (the part of the bill spent on from_model) and the quality difference. Labelled as an estimate from one public benchmark. For any other pair it does not guess and offers the free pilot that measures your own tasks.

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": {
      "monthly_bill_usd": "<monthly_bill_usd>",
      "from_model": "<from_model>",
      "to_model": "<to_model>"
    },
    "name": "estimate_switch_savings"
  }
}

Input Schema

Name	Required	Description	Default
`to_model`	Yes
`from_model`	Yes
`monthly_bill_usd`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the supported model set (Claude Opus, Sonnet, Haiku 5.5 on Aider), states the numbers come from one public benchmark and are labelled as estimates, and says it refuses to extrapolate outside that set. Remaining gap is the exact behavior for an unsupported pair (error vs. a message plus pilot offer) and any cost/latency for the estimate itself.

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?

Front-loaded trigger, then capability, then the measurement caveat and fallback — a sensible order with little waste. It runs slightly long for three parameters and the nested quoting is awkward, but no sentence is redundant.

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 three-parameter estimation tool with an output schema already defining the return shape, the description covers trigger, supported inputs, the meaning of the bill parameter, the reliability caveat, and the fallback path. An agent can decide to call it and pass correct arguments without further information.

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 0%, so the description must compensate, and it does for the non-obvious parameter: monthly_bill_usd is defined as only the portion of the bill spent on from_model, a constraint an agent would otherwise get wrong. It also names the acceptable model families, though it never states that from_model/to_model strings must match that list exactly.

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?

Specific verb+resource: it returns a measured cost-per-solved-task ratio plus the arithmetic on monthly_bill_usd and the quality delta for a model pair. It also scopes the tool to pairs the vendor actually measured, which separates it from generic pricing/usage siblings.

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?

Opens with an explicit trigger phrase ("Use when asked 'how much would we save by switching from model A to model B?'") and an explicit exclusion: for unmeasured pairs it declines to guess and points to the free pilot. Both the when and the when-not are stated.

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

Deploy Server