ground-truth-mcp

Claim Support Check

verify_claim

Read-onlyIdempotent

Check whether a factual claim is supported by provided evidence URLs. Uses keyword matching to determine if each source supports the claim.

Instructions

Check whether a factual claim is supported by a specific set of public evidence URLs that you already have. For each source, the tool performs a case-insensitive keyword match over the fetched page body, then marks that source as supporting the claim when at least half of the supplied keywords appear. Use this for evidence-backed claim checks on known pages, not for open-ended search, semantic reasoning, or contradiction extraction. The aggregate verdict is driven only by the per-page keyword support ratio. Fetched pages are cached for 5 minutes.

Input Schema

TableJSON Schema

Name	Required	Description
`claim`	Yes	Plain-language claim to verify, for example 'AWS Business support includes 24/7 phone support'.
`evidence_urls`	Yes	One to ten public documentation, pricing, policy, or support URLs that are likely to contain direct evidence for the claim.
`keywords`	Yes	Keywords or short phrases that should appear on supporting pages. Matching is case-insensitive substring matching, so choose phrases that are likely to appear verbatim.

Output Schema

TableJSON Schema

Name	Required	Description
`claim`	Yes	Claim that was evaluated.
`sources`	Yes	Per-source evidence results.
`verdict`	Yes	Aggregate verdict across all supplied sources.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.4.0May 5, 2026

changedInput schema / properties / keywords / description

Previous value: -"Keywords or short phrases that should appear on supporting pages. Matching is case-insensitive substring matching."New value: +"Keywords or short phrases that should appear on supporting pages. Matching is case-insensitive substring matching, so choose phrases that are likely to appear verbatim."

changedOutput schema / properties / verdict / properties / summary / description

Previous value: -"High-level verdict derived from the supporting-source ratio."New value: +"High-level verdict derived from the supporting-source ratio: all sources supporting => CONFIRMED, none => UNCONFIRMED, majority => LIKELY TRUE, otherwise LIKELY FALSE."

Changed6 schema fields changedv0.1.1Apr 30, 2026

changedInput schema / properties / claim / description

Previous value: -"The factual claim to verify"New value: +"Plain-language claim to verify, for example 'AWS Business support includes 24/7 phone support'."

addedInput schema / properties / claim / minLength
```
Added value: +5
```

changedInput schema / properties / evidence_urls / description

Previous value: -"URLs to cross-reference against"New value: +"One to ten public documentation, pricing, policy, or support URLs that are likely to contain direct evidence for the claim."

changedInput schema / properties / keywords / description

Previous value: -"Keywords that should appear if the claim is true"New value: +"Keywords or short phrases that should appear on supporting pages. Matching is case-insensitive substring matching."

addedInput schema / properties / keywords / items / minLength
```
Added value: +1
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "claim": {
+      "description": "Claim that was evaluated.",
+      "type": "string"
+    },
+    "sources": {
+      "description": "Per-source evidence results.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "accessible": {
+            "description": "True when the evidence page could be fetched.",
+            "type": "boolean"
+          },
+          "cached": {
+            "description": "True when the page body came from the 5-minute cache.",
+            "type": "boolean"
+          },
+          "error": {
+            "description": "Fetch error when the evidence page could not be checked.",
+            "type": "string"
+          },
+          "keywordsMatched": {
+            "description": "Subset of supplied keywords that were found on the page.",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "keywordsTotal": {
+            "description": "Total number of keywords the tool looked for on this page.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "matchRatio": {
+            "description": "Matched-keyword ratio for this source, from 0 to 1.",
+            "maximum": 1,
+            "minimum": 0,
+            "type": "number"
+          },
+          "supports": {
+            "description": "True when the page met the current support threshold of at least half of the supplied keywords.",
+            "type": "boolean"
+          },
+          "url": {
+            "description": "Evidence URL that was checked.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "url",
+          "accessible",
+          "supports"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "verdict": {
+      "additionalProperties": false,
+      "description": "Aggregate verdict across all supplied sources.",
+      "properties": {
+        "confidence": {
+          "description": "Share of sources that supported the claim.",
+          "maximum": 1,
+          "minimum": 0,
+          "type": "number"
+        },
+        "contradicting": {
+          "description": "Number of sources not marked as supporting the claim.",
+          "minimum": 0,
+          "type": "integer"
+        },
+        "summary": {
+          "description": "High-level verdict derived from the supporting-source ratio.",
+          "enum": [
+            "CONFIRMED",
+            "UNCONFIRMED",
+            "LIKELY TRUE",
+            "LIKELY FALSE"
+          ],
+          "type": "string"
+        },
+        "supporting": {
+          "description": "Number of sources marked as supporting the claim.",
+          "minimum": 0,
+          "type": "integer"
+        },
+        "total": {
+          "description": "Total number of evidence sources checked.",
+          "minimum": 0,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "supporting",
+        "contradicting",
+        "total",
+        "confidence",
+        "summary"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "claim",
+    "sources",
+    "verdict"
+  ],
+  "type": "object"
+}

First observedv0.1.0Apr 29, 2026

TDQS

A5/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint, idempotentHint), the description adds the algorithm: case-insensitive keyword match, half-threshold for support, cache duration. No contradiction with annotations.

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?

Front-loaded with primary action, each sentence adds value, no unnecessary words. Length is appropriate for the tool's complexity.

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?

Covers all necessary aspects: purpose, when to use, algorithm, caching. Given the presence of an output schema for return values, the description is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, the description adds meaningful context: explains the matching is case-insensitive substring and suggests choosing phrases verbatim, and clarifies the half-keyword threshold for support.

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 specifies the verb 'check' and resource 'factual claim supported by evidence URLs', and distinguishes from siblings by explicitly stating it is not for open-ended search, semantic reasoning, or contradiction extraction.

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

Usage Guidelines5/5

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

Explicitly states when to use ('evidence-backed claim checks on known pages') and when not to use ('not for open-ended search...'), with clear context about keyword matching and caching.

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

Deploy Server