Source Claim Proof

by dev.workers.mattskowronis.source-claim-proof

Verify Source Claim

verify_source_claim

Read-onlyIdempotent

Verify one atomic factual claim against one public source URL. Return supported, contradicted, or insufficient-evidence with source snippets, or explicit blocked/unreachable/unsupported states. Not a general fact checker.

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": {
      "url": "<url>",
      "claim": "<claim>"
    },
    "name": "verify_source_claim"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Public HTTP or HTTPS source page URL to inspect.
`claim`	Yes	One atomic factual assertion to check against that source only.

Output Schema

Name	Required	Description
`claim`	Yes	The claim that was checked.
`verdict`	Yes	supported, contradicted, or insufficient_evidence.
`evidence`	Yes	Compact source snippets used for the verdict.
`final_url`	Yes	Final URL after redirects.
`source_url`	Yes	Requested source URL.
`content_hash`	Yes	Hash of retrieved source content.
`retrieved_at`	Yes	UTC timestamp of the check.
`source_status`	Yes	verified, blocked, unreachable, unsupported, or insufficient_evidence.
`service_version`	Yes	Source Claim Proof service version.
`retrieval_method`	Yes	How the source page was fetched.
`reasoning_summary`	Yes	Short machine-readable reason for the verdict.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 19, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "claim": {
+      "description": "The claim that was checked.",
+      "type": "string"
+    },
+    "content_hash": {
+      "description": "Hash of retrieved source content.",
+      "type": "string"
+    },
+    "evidence": {
+      "description": "Compact source snippets used for the verdict.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "evidence_type": {
+            "description": "Where the snippet came from on the source page.",
+            "enum": [
+              "visible_text",
+              "heading",
+              "json_ld",
+              "meta",
+              "status"
+            ],
+            "type": "string"
+          },
+          "location": {
+            "description": "Page location of the snippet, or null if unknown.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "polarity": {
+            "description": "Whether the snippet supports, contradicts, or is neutral.",
+            "enum": [
+              "supports",
+              "contradicts",
+              "neutral"
+            ],
+            "type": "string"
+          },
+          "text": {
+            "description": "Source snippet that supports or contradicts the claim.",
+            "maxLength": 240,
+            "type": "string"
+          }
+        },
+        "required": [
+          "text",
+          "location",
+          "evidence_type",
+          "polarity"
+        ],
+        "type": "object"
+      },
+      "maxItems": 3,
+      "type": "array"
+    },
+    "final_url": {
+      "description": "Final URL after redirects.",
+      "type": "string"
+    },
+    "reasoning_summary": {
+      "description": "Short machine-readable reason for the verdict.",
+      "maxLength": 400,
+      "type": "string"
+    },
+    "retrieval_method": {
+      "description": "How the source page was fetched.",
+      "enum": [
+        "direct_http",
+        "browser_run",
+        "official_api",
+        "unsupported"
+      ],
+      "type": "string"
+    },
+    "retrieved_at": {
+      "description": "UTC timestamp of the check.",
+      "type": "string"
+    },
+    "service_version": {
+      "description": "Source Claim Proof service version.",
+      "type": "string"
+    },
+    "source_status": {
+      "description": "verified, blocked, unreachable, unsupported, or insufficient_evidence.",
+      "enum": [
+        "verified",
+        "blocked",
+        "unreachable",
+        "unsupported",
+        "insufficient_evidence"
+      ],
+      "type": "string"
+    },
+    "source_url": {
+      "description": "Requested source URL.",
+      "type": "string"
+    },
+    "verdict": {
+      "description": "supported, contradicted, or insufficient_evidence.",
+      "enum": [
+        "supported",
+        "contradicted",
+        "insufficient_evidence"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "verdict",
+    "claim",
+    "source_url",
+    "final_url",
+    "source_status",
+    "evidence",
+    "reasoning_summary",
+    "retrieval_method",
+    "retrieved_at",
+    "content_hash",
+    "service_version"
+  ],
+  "type": "object"
+}

First observedAug 19, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true. The description adds behavioral context by specifying possible return states ('supported, contradicted, or insufficient-evidence') and handling of blocked/unreachable sources, which is valuable beyond the 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?

The description is two sentences long, front-loaded with the primary purpose, and every phrase adds value. It is concise without omitting critical behavioral states or scope limitations.

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?

Given the simple two-parameter schema, the presence of an output schema, and strong annotations, the description covers the essential behavior including return states and non-general-fact-checker scope. It could have added a bit more detail on expected source snippet formatting, but that is not necessary given the output schema.

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?

The input schema already provides complete descriptions for both parameters (100% schema coverage). The description reinforces the semantics with 'atomic factual claim' and 'public source URL' but does not add new information beyond the schema.

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 uses specific verb 'Verify' with a clear resource: 'one atomic factual claim against one public source URL.' It explicitly distinguishes itself from general fact checking with 'Not a general fact checker,' which clarifies its unique scope.

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 clearly states the intended use case (verifying a single claim against a single URL) and provides an explicit exclusion ('Not a general fact checker'). However, it does not name any alternative tools, though none are present in sibling tools.

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

All Source Claim Proof tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?