WhitePact

Check Text Against Governance Policy

rai_policy_check

Read-onlyIdempotent

Evaluate text or model responses against a governance policy to check blocked topics, keywords, length, PII, and required disclaimers, returning pass/fail per rule with fixes.

Instructions

Evaluate text or a model response against a governance policy. Checks for: prohibited topics, required disclaimers, output length limits, language restrictions, and custom keyword blocklist. Returns pass/fail per policy rule with remediation guidance.

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": {
      "text": "<text>",
      "policy": "<policy>"
    },
    "name": "rai_policy_check"
  }
}

Input Schema

Name	Required	Description	Default
`text`	Yes	Text to evaluate against policy
`policy`	Yes	Governance policy configuration

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?

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation behavior: the check categories performed and the fact that output is pass/fail per rule with remediation guidance — important since there is no output schema.

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?

Three tight sentences: purpose first, then the rule inventory, then the return shape. No filler and nothing redundant with structured fields, and the most decision-relevant content is front-loaded.

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?

With no output schema but a nested policy object, the description carries real weight and discharges most of it by stating the return shape and the rule set. The gap is the 'language restrictions' claim, which no schema property supports, and the absence of any note on how PII checking defaults (the schema sets require_pii_clean=true).

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 the baseline is 3 and the schema already documents every policy key. The description loosely mirrors those keys (prohibited topics, disclaimers, length limits, keyword blocklist) but adds no syntax, format or defaulting detail, and its mention of 'language restrictions' corresponds to no field in the schema.

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 gives a specific verb ('Evaluate') and resource ('text or a model response against a governance policy') and enumerates the exact rule classes checked, so an agent knows precisely what this tool produces. It does not, however, name or contrast itself with close siblings such as rai_scan or rai_compliance, leaving the agent to infer the boundary.

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?

Usage is only implied by the object being evaluated ('text or a model response'), with no explicit when-to-use, when-not-to-use, or alternative named among the ~29 rai_* siblings. Given the crowded namespace (rai_scan, rai_compliance, rai_memory_write_check), a routing sentence would be expected.

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