Skip to main content
Glama

Extract claims

extract_claims
Read-onlyIdempotent

Split a text (for example an AI-generated answer) into atomic factual claims. Each claim includes span, grounding_required, claim_type (number|date|quantity|quote|named_entity_fact|comparison|opinion|prediction|other), check_worthiness (high|medium|low), and the source sentence. Hedges are stripped, pronouns are resolved across sentences, and compound sentences are split. Questions, greetings, opinions and predictions are marked grounding_required false. Up to 3 checkable factual claims (opinions skipped) get a next_step: a ready-to-send quick_check request ($0.15, fast verdict with 1-2 sources), with deep_verify ($0.75) and verify_claim ($1.00) bodies in next_step.alternatives, so you can check them in one more call. Price: $0.05 USDC on Base per call via x402; this MCP call returns payment instructions and POST /v1/extract_claims returns the claims. Read-only.

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>"
    },
    "name": "extract_claims"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe text to split into claims, for example a chatbot answer. Up to a few thousand characters.

Output Schema

NameRequiredDescriptionDefault
toolYesTool name.
resultNoPaid result: { claims: [{ claim_id, text, span, grounding_required, claim_type, check_worthiness, sentence, sentence_index, next_step?: { tool, why, price_usd, endpoint, method, body, alternatives[] } }], recommended_next_steps: { tool, count, total_price_usd, options[] }, summary, priced_usd }.
statusYespayment_required: pay the HTTP route with x402 to get the result. ok: result is included.
messageYesHuman-readable summary.
paymentNoPayment instructions. MCP tools/call does not charge or run the paid work; call the HTTP route with x402.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedOutput schema / properties / result / description
      Previous value: -"Paid result: { claims: [{ claim_id, text, span, grounding_required, claim_type, check_worthiness, sentence, sentence_index, next_step? }], recommended_next_steps, summary, priced_usd }."New value: +"Paid result: { claims: [{ claim_id, text, span, grounding_required, claim_type, check_worthiness, sentence, sentence_index, next_step?: { tool, why, price_usd, endpoint, method, body, alternatives[] } }], recommended_next_steps: { tool, count, total_price_usd, options[] }, summary, priced_usd }."
    • changedOutput schema / properties / result / properties / claims / items / properties / next_step / description
      Previous value: -"1.4.8: present only on unsure, low-confidence or unverified high-worthiness claims. A ready-to-send Deep verify request for this claim (optional, paid separately)."New value: +"Present only on unsure or low-confidence claims (check_answer) or unverified high/medium-worthiness factual claims (extract_claims; opinions and predictions skipped; max 3 per response). A ready-to-send request for this claim (optional, paid separately): Quick check ($0.15) from extract_claims, Deep verify from check_answer and quick_check. extract_claims adds alternatives[] with ready-to-send Quick check ($0.15), Deep verify ($0.75) and Verify claim ($1.00) requests."
    • addedOutput schema / properties / result / properties / claims / items / properties / next_step / properties / alternatives
      Added value: +{
      +  "description": "1.4.9 (extract_claims): every ready-to-send paid check for this claim. POST body to endpoint with an x402 client.",
      +  "items": {
      +    "properties": {
      +      "body": {
      +        "type": "object"
      +      },
      +      "endpoint": {
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "method": {
      +        "const": "POST",
      +        "type": "string"
      +      },
      +      "price_usd": {
      +        "type": "number"
      +      },
      +      "tool": {
      +        "enum": [
      +          "quick_check",
      +          "deep_verify",
      +          "verify_claim"
      +        ],
      +        "type": "string"
      +      },
      +      "when": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "tool",
      +      "price_usd",
      +      "endpoint",
      +      "method",
      +      "body"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • removedOutput schema / properties / result / properties / claims / items / properties / next_step / properties / tool / const
      Removed value: -"deep_verify"
    • addedOutput schema / properties / result / properties / claims / items / properties / next_step / properties / tool / description
      Added value: +"1.5.0: quick_check from extract_claims; deep_verify from check_answer and quick_check."
    • addedOutput schema / properties / result / properties / claims / items / properties / next_step / properties / tool / enum
      Added value: +[
      +  "quick_check",
      +  "deep_verify"
      +]
    • addedOutput schema / properties / result / properties / recommended_next_steps / properties / options
      Added value: +{
      +  "description": "1.4.9 (extract_claims): cost to check all suggested claims with each tool.",
      +  "items": {
      +    "properties": {
      +      "endpoint": {
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "price_usd_each": {
      +        "type": "number"
      +      },
      +      "tool": {
      +        "type": "string"
      +      },
      +      "total_price_usd": {
      +        "type": "number"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  2. Changed3 schema fields changed
    • changedOutput schema / properties / result / description
      Previous value: -"Paid result: { claims: [{ claim_id, text, span, grounding_required, claim_type, check_worthiness, sentence, sentence_index }], summary, priced_usd }."New value: +"Paid result: { claims: [{ claim_id, text, span, grounding_required, claim_type, check_worthiness, sentence, sentence_index, next_step? }], recommended_next_steps, summary, priced_usd }."
    • addedOutput schema / properties / result / properties / claims / items / properties
      Added value: +{
      +  "next_step": {
      +    "description": "1.4.8: present only on unsure, low-confidence or unverified high-worthiness claims. A ready-to-send Deep verify request for this claim (optional, paid separately).",
      +    "properties": {
      +      "body": {
      +        "properties": {
      +          "claim": {
      +            "properties": {
      +              "text": {
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "text"
      +            ],
      +            "type": "object"
      +          }
      +        },
      +        "required": [
      +          "claim"
      +        ],
      +        "type": "object"
      +      },
      +      "endpoint": {
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "method": {
      +        "const": "POST",
      +        "type": "string"
      +      },
      +      "price_usd": {
      +        "type": "number"
      +      },
      +      "tool": {
      +        "const": "deep_verify",
      +        "type": "string"
      +      },
      +      "why": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "tool",
      +      "why",
      +      "price_usd",
      +      "endpoint",
      +      "method",
      +      "body"
      +    ],
      +    "type": "object"
      +  }
      +}
    • addedOutput schema / properties / result / properties / recommended_next_steps
      Added value: +{
      +  "description": "1.4.8: summary of claim-level next_step suggestions.",
      +  "properties": {
      +    "count": {
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "endpoint": {
      +      "format": "uri",
      +      "type": "string"
      +    },
      +    "note": {
      +      "type": "string"
      +    },
      +    "tool": {
      +      "type": "string"
      +    },
      +    "total_price_usd": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "tool",
      +    "count",
      +    "total_price_usd"
      +  ],
      +  "type": "object"
      +}
  3. Changed2 schema fields changed
    • changedOutput schema / properties / result / description
      Previous value: -"Paid result: { claims: [{ claim_id, text, span: { start, end }, grounding_required }], priced_usd }."New value: +"Paid result: { claims: [{ claim_id, text, span, grounding_required, claim_type, check_worthiness, sentence, sentence_index }], summary, priced_usd }."
    • addedOutput schema / properties / result / properties / summary
      Added value: +{
      +  "type": "object"
      +}
  4. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations it discloses genuinely unusual behavior an agent must know: hedges are stripped, pronouns are resolved across sentences, compound sentences are split, and questions/greetings/opinions/predictions are flagged grounding_required=false. It also reveals the two-step payment protocol — this MCP call returns payment instructions while POST /v1/extract_claims returns claims — and the $0.05 USDC on Base x402 cost, which is critical to avoid misreading the first response as a failure.

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?

Front-loaded with the core action, then output fields, then behavioral transforms, then the monetization/next-step mechanics — a sensible priority order. The pricing and next_step sentence is dense but each clause carries decision-relevant information; the field enum list is long but unavoidable.

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?

Covers cost, payment flow, output field meanings, and downstream options, which is more than enough for a single-string input tool with an output schema. Some of the output-field explanation duplicates the output schema, and it does not describe error or latency behavior, so it falls just short of fully complete.

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% and the single `text` parameter is already documented with an example and a length bound, so the description adds little parameter-level meaning. It only implies the input is typically an AI-generated answer, which the schema example already conveys. 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?

"Split a text ... into atomic factual claims" names a specific verb and resource, and the surrounding text makes clear this is the extraction stage that feeds the sibling verification tools (quick_check, deep_verify, verify_claim). An agent can distinguish it from check_answer or verify_claim without opening any schema.

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 makes the upstream position in the pipeline explicit: extract first, then up to 3 checkable claims come back with a ready-to-send next_step and priced alternatives, "so you can check them in one more call." It never states the contrast case (when to skip extraction and call check_answer or quick_check directly), so the routing is strong but not exhaustive.

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.