WhitePact

Analyze Red Team Responses

rai_redteam_analyze

Read-onlyIdempotent

Analyze model responses to red-team attack payloads and return a security report with vulnerability findings, severity breakdown, and an overall security score.

Instructions

Analyse model responses to red team attack payloads. Returns a security report with vulnerability findings, severity breakdown, and an overall security score.

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>",
      "responses": "<responses>"
    },
    "name": "rai_redteam_analyze"
  }
}

Input Schema

Name	Required	Description
`provider`	Yes
`responses`	Yes	Map of attack_name → model_response_text
`model_name`	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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral value by stating the return shape: vulnerability findings, severity breakdown, and an overall security score, which matters because no output schema exists. It still omits any note on cost, latency, or whether the analysis is deterministic across runs.

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 sentences, front-loaded with the action and closed with the return contents; every clause carries information and there is no padding. It could be marginally tighter by combining the report contents, but it is appropriately sized.

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 correctly spends its budget describing the returned security report, which is the most important omission it could fill. However, for a three-parameter tool with a nested input object and no parameter documentation, the definition leaves the agent guessing about what provider and model_name should contain and where the responses are sourced from.

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 only 33%, and the description adds no information about any of the three required parameters. The nested responses map is documented in the schema, but provider and model_name are unexplained in both places, so the description fails to compensate for the coverage gap.

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: analyse model responses to red team attack payloads, and it names the artifact being analyzed (responses to attack payloads), which separates it from sibling tools like rai_redteam_payloads. It stops short of explicitly naming which sibling to use instead or when this differs from rai_scan or rai_bias_evaluate, so it is clear but not fully differentiated.

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?

There is no when-to-use guidance, no statement of prerequisites (e.g., that responses must first come from rai_redteam_payloads or rai_scan), and no conditions under which this tool should be preferred over alternatives such as rai_trust_score. The agent must infer usage entirely from the tool name and description.

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