world-model-mcp

verify_retrieval

Verify an answer's claims against supplied facts, returning confidence (HIGH/MEDIUM/LOW), verified/unverified claim lists, and per-claim source pointers.

Instructions

Adversarially verify an answer is grounded in a specific set of facts. An independent Coach LLM call checks each material claim in the answer against the supplied source facts and returns confidence (HIGH / MEDIUM / LOW), verified + unverified claim lists, and per-claim source_pointers. Never raises; failures return LOW + error populated. v0.12.12.

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": {
      "query": "<query>",
      "answer": "<answer>",
      "fact_ids": "<fact_ids>"
    },
    "name": "verify_retrieval"
  }
}

Input Schema

Name	Required	Description
`query`	Yes	The user query the answer responds to
`answer`	Yes	The candidate answer under verification
`fact_ids`	Yes	IDs of facts the caller believes ground the answer. Missing IDs are silently dropped.
`verification_model`	No	Optional Coach model override. Defaults to config.verification_model (Haiku 4.5).

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.12.13Jul 7, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With no annotations, the description carries full burden. It discloses the independent Coach LLM call, the confidence levels (HIGH/MEDIUM/LOW), the verified and unverified claim lists, per-claim source_pointers, and that it never raises (failures return LOW with error populated). This is excellent behavioral transparency.

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?

The description is concise and front-loaded with the core purpose, followed by behavior and return details. The version tag 'v0.12.12' adds minor noise but does not detract significantly. Overall, every sentence earns its place.

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?

Since there is no output schema, the description fully explains return values (confidence, claim lists, source_pointers) and error behavior. It is complete for a verification tool, covering what the agent needs to know to invoke it correctly and interpret results.

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 100%, so baseline is 3. The description does not add parameter-specific semantics beyond what the schema already provides; it references 'supplied source facts' but leaves parameter details to the schema. This is adequate but not additive.

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?

The description opens with a specific verb+resource: 'Adversarially verify an answer is grounded in a specific set of facts.' It clearly distinguishes the tool from sibling tools like query_fact or validate_change by emphasizing adversarial verification against supplied source facts.

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

Usage Guidelines4/5

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

The description gives clear context for when to use this tool: whenever an answer needs to be checked against a set of facts. It implies the use case without explicit exclusion or alternative reference, but the context is strong enough to guide selection.

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