WhitePact

Check Trust Score Drift

rai_drift_check

Read-onlyIdempotent

Detect trust score drift between baseline and current evaluations; report per-dimension deltas, overall severity, and whether alert thresholds were breached.

Instructions

Detect trust score drift between a baseline evaluation and a current evaluation. Returns drift delta per dimension, overall drift severity (NONE/LOW/MEDIUM/HIGH/CRITICAL), and whether an alert threshold was breached.

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_name": "<model_name>",
      "provider": "<provider>",
      "baseline_score": "<baseline_score>",
      "current_score": "<current_score>"
    },
    "name": "rai_drift_check"
  }
}

Input Schema

Name	Required	Description
`provider`	Yes
`model_name`	Yes
`current_score`	Yes	Current trust dimension scores (0-1 each)
`baseline_score`	Yes	Previous trust dimension scores (0-1 each)
`alert_threshold`	No	Overall score drop (0-100 scale) that triggers an alert

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.6Sep 11, 2026

TDQS

A3.8/5.0

Behavior4/5

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

The annotations already disclose read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral detail beyond that: it returns per-dimension drift deltas, a five-level severity value (NONE/LOW/MEDIUM/HIGH/CRITICAL), and an alert-threshold breach indicator. It does not cover auth or rate limits, but those are minor for this read-only analysis tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first states the purpose, the second states the return values. It is front-loaded, has no filler, and every clause contributes useful information.

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?

For a read-only tool with no output schema, the description explains the core purpose and the main return fields, including severity levels and threshold breach detection. It remains silent on when to choose it over sibling trust tools and on the two parameters lacking schema descriptions, which keeps it from a 5.

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 coverage is 60%: baseline_score, current_score, and alert_threshold have schema descriptions, while provider and model_name do not. The description reinforces the baseline/current comparison and alert-threshold concept but adds no semantics for the two undocumented parameters. A 3 is appropriate given the moderate schema coverage.

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 uses a specific verb (detect) and resource (trust score drift), and scopes it to a baseline evaluation versus a current evaluation. It also names the return outputs, so the purpose is clear. It does not, however, explicitly differentiate itself from sibling tools such as rai_check_trust or rai_trust_score, which keeps it from a 5.

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 baseline/current framing implies when the tool is useful, namely when comparing two trust-score evaluations. There is no explicit when-to-use, when-not-to-use, or named alternative, so an agent must infer that this is preferable to rai_trust_score or rai_check_trust for drift analysis.

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