Skip to main content
Glama

KARP Research by SoulDriver

Fact-check one claim live ($0.25)

karp_check
Read-only

Hallucination check from SoulDriver: a live fact-check of one claim by four AI models (GPT, Gemini, Grok, Claude), each searching the web separately. Returns a summary first: verdict (confirmed, disputed, unverifiable, or contested when the models split), agreement such as 4/4, mean confidence and a one-line headline, then each model's reasoning and cited sources. Price $0.25: pay with x402, or pass grant_key from karp_grant_apply. 10-45 s.

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": {
      "claim": "<claim>"
    },
    "name": "karp_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
claimYesOne factual claim to check
grant_keyNoOptional: a research grant key from karp_grant_apply. Pays for this call instead of x402 while the grant lasts.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld and non-idempotent, and the description adds substantial context beyond them: the verdict vocabulary (confirmed/disputed/unverifiable/contested), the agreement ratio, mean confidence, per-model reasoning with cited sources, the $0.25 price, the two payment paths, and a 10-45 s latency expectation. It does not explain failure modes (e.g. what happens if a model errors or the grant is exhausted), which keeps it short of a 5.

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 return shape is front-loaded ('Returns a summary first') and every sentence carries information — verdicts, price, latency. It is dense and slightly run-on, but no sentence is filler.

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, the description carries the burden of describing returns and does so thoroughly, plus cost and latency. The only gap is error/edge-case behavior for a paid, non-idempotent call, which an agent would want before spending $0.25.

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 both parameters are already documented, including the grant_key's payment semantics. The description restates the grant_key alternative but adds no syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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 states a specific verb and resource — a live fact-check of one claim — and adds the mechanism (four named AI models each searching the web separately). An agent can tell this apart from a general Q&A sibling like karp_ask without opening the schema.

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 implied by the scope ('one factual claim') and the payment routing (x402 or a grant_key from karp_grant_apply) is spelled out, but there is no explicit when-to-use/when-not guidance relative to siblings such as karp_ask or karp_coverage. The agent must infer that this is the deep, paid verification path.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources