WhitePact

Compare Two Models' Trust Scores

rai_compare_models

Read-onlyIdempotent

Compare two AI models across six trust dimensions to get scores, delta analysis, and a recommendation on which is more trustworthy.

Instructions

Compare two AI models across all six trust dimensions. Returns scores for each, delta analysis, and a recommendation on which model is more trustworthy.

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_a": "<model_a>",
      "provider_a": "<provider_a>",
      "model_b": "<model_b>",
      "provider_b": "<provider_b>"
    },
    "name": "rai_compare_models"
  }
}

Input Schema

Name	Required	Description	Default
`model_a`	Yes
`model_b`	Yes
`scores_a`	No
`scores_b`	No
`provider_a`	Yes
`provider_b`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.6Sep 11, 2026

TDQS

B3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description usefully supplements by disclosing the return shape (per-model scores, delta analysis, recommendation), which matters since there is no output schema. It says nothing about auth requirements or where the scores come from when scores_a/scores_b aren't supplied.

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?

Two tidy sentences, front-loaded with the operation and followed by the return content. No filler, though it could have spent one of those sentences on parameter guidance instead of repeating the count of dimensions.

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?

With no output schema, the description's summary of returns is genuinely necessary and present. However, for a six-parameter tool with nested objects, 0% schema coverage, and four required inputs, the omission of any input semantics leaves the definition only partially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across six parameters, so the description carries the full burden and falls short. It hints at 'six trust dimensions' but never clarifies the distinction between the required model_a/provider_a/model_b/provider_b and the optional nested scores_a/scores_b objects, nor what happens if scores are omitted.

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 states a specific verb and resource (compare two AI models) and scopes it to 'all six trust dimensions', which is concrete. It does not explicitly distinguish itself from the single-model sibling rai_trust_score, but the two-model framing is self-evident from the name and title.

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

Usage Guidelines2/5

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

No when-to-use or when-not-to-use guidance is given, and no alternative is named despite several closely related siblings (rai_trust_score, rai_benchmark, rai_model_route). The comparison purpose is implied by 'compare two models' but the agent is left to infer when this is the right tool.

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