Web Evidence

Verify claim (deep)

verify_claim_deep

Deep verification for compound or contested claims using up to 15 cited sources. Costs $0.12 USDC on Base per call.

Input Schema

TableJSON Schema

Name	Required	Description
`asOf`	No	Optional YYYY-MM-DD date at which the claim should be evaluated.
`claim`	Yes	The factual claim to verify.
`language`	No	Preferred response language or auto for automatic selection. Defaults to auto.
`maxSources`	No	Maximum number of evidence sources to return, capped by the selected verification tier.
`jurisdiction`	No	Optional country, state, or legal jurisdiction that should frame the verification.
`sourcePolicy`	No	Source selection policy. Defaults to authoritative; official_only requires allowedDomains.
`allowedDomains`	No	Optional hostname allowlist without schemes or paths, for example openai.com.
`blockedDomains`	No	Optional hostname blocklist without schemes or paths.
`freshnessHours`	No	Maximum preferred source age in hours. Defaults to 168 hours.
`minimumSources`	No	Minimum number of sources requested. Defaults to 2 and cannot exceed maxSources.
`includeConflicts`	No	Whether to search for and report conflicting evidence. Defaults to true.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`claim`	Yes
`status`	Yes
`commerce`	Yes
`evidence`	Yes
`conflicts`	Yes
`snapshots`	Yes
`conclusion`	Yes
`observedAt`	Yes
`provenance`	Yes
`atomicFacts`	Yes
`limitations`	Yes
`verificationId`	Yes
`providerSources`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 3, 2026

addedInput schema / properties / allowedDomains / description

Added value: +"Optional hostname allowlist without schemes or paths, for example openai.com."

addedInput schema / properties / blockedDomains / description

Added value: +"Optional hostname blocklist without schemes or paths."

addedInput schema / properties / freshnessHours / description

Added value: +"Maximum preferred source age in hours. Defaults to 168 hours."

addedInput schema / properties / includeConflicts / description

Added value: +"Whether to search for and report conflicting evidence. Defaults to true."

addedInput schema / properties / jurisdiction / description

Added value: +"Optional country, state, or legal jurisdiction that should frame the verification."

addedInput schema / properties / language / description

Added value: +"Preferred response language or auto for automatic selection. Defaults to auto."

addedInput schema / properties / maxSources / description

Added value: +"Maximum number of evidence sources to return, capped by the selected verification tier."

addedInput schema / properties / minimumSources / description

Added value: +"Minimum number of sources requested. Defaults to 2 and cannot exceed maxSources."

addedInput schema / properties / sourcePolicy / description

Added value: +"Source selection policy. Defaults to authoritative; official_only requires allowedDomains."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "atomicFacts": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "confidence": {
+            "maximum": 1,
+            "minimum": 0,
+            "type": "number"
+          },
+          "evidenceIds": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "explanation": {
+            "type": "string"
+          },
+          "statement": {
+            "type": "string"
+          },
+          "status": {
+            "enum": [
+              "confirmed",
+              "partially_confirmed",
+              "contradicted",
+              "insufficient_evidence",
+              "ambiguous"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "statement",
+          "status",
+          "confidence",
+          "explanation",
+          "evidenceIds"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "claim": {
+      "type": "string"
+    },
+    "commerce": {
+      "additionalProperties": false,
+      "properties": {
+        "orderId": {
+          "type": "string"
+        },
+        "orderToken": {
+          "type": "string"
+        },
+        "orderUrl": {
+          "format": "uri",
+          "type": "string"
+        },
+        "receiptId": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "orderId",
+        "orderToken",
+        "receiptId",
+        "orderUrl"
+      ],
+      "type": "object"
+    },
+    "conclusion": {
+      "type": "string"
+    },
+    "conflicts": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "evidenceIds": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "summary": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "summary",
+          "evidenceIds"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "evidence": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "cited": {
+            "type": "boolean"
+          },
+          "consulted": {
+            "type": "boolean"
+          },
+          "excerpt": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "providerSourceMatched": {
+            "type": "boolean"
+          },
+          "publishedAt": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "publisher": {
+            "type": "string"
+          },
+          "qualityReason": {
+            "type": "string"
+          },
+          "relationship": {
+            "enum": [
+              "supports",
+              "contradicts",
+              "context"
+            ],
+            "type": "string"
+          },
+          "retrievedAt": {
+            "format": "date-time",
+            "type": "string"
+          },
+          "snapshotId": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "snapshotted": {
+            "type": "boolean"
+          },
+          "sourceType": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "url": {
+            "format": "uri",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "url",
+          "title",
+          "publisher",
+          "publishedAt",
+          "retrievedAt",
+          "excerpt",
+          "relationship",
+          "sourceType",
+          "qualityReason",
+          "providerSourceMatched",
+          "cited",
+          "snapshotId",
+          "consulted",
+          "snapshotted"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "limitations": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "observedAt": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "provenance": {
+      "additionalProperties": false,
+      "properties": {
+        "cacheHit": {
+          "type": "boolean"
+        },
+        "cachedInputTokens": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "citedSourceCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "consultedSourceCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "inputTokens": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "matchedEvidenceCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "model": {
+          "type": "string"
+        },
+        "outputTokens": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "provider": {
+          "type": "string"
+        },
+        "providerResponseId": {
+          "type": "string"
+        },
+        "providerSourceCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "searchedWeb": {
+          "type": "boolean"
+        },
+        "snapshottedSourceCount": {
+          "minimum": 0,
+          "type": "integer"
+        },
+        "webSearchCallCount": {
+          "minimum": 0,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "provider",
+        "model",
+        "providerResponseId",
+        "searchedWeb",
+        "consultedSourceCount",
+        "citedSourceCount",
+        "providerSourceCount",
+        "matchedEvidenceCount",
+        "snapshottedSourceCount",
+        "webSearchCallCount",
+        "inputTokens",
+        "cachedInputTokens",
+        "outputTokens",
+        "cacheHit"
+      ],
+      "type": "object"
+    },
+    "providerSources": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "actions": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "cited": {
+            "type": "boolean"
+          },
+          "evidenceIds": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "provider": {
+            "type": "string"
+          },
+          "queries": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "searchCallIds": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "snapshotId": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "sourceId": {
+            "type": "string"
+          },
+          "title": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "format": "uri",
+            "type": "string"
+          }
+        },
+        "required": [
+          "sourceId",
+          "url",
+          "title",
+          "provider",
+          "searchCallIds",
+          "actions",
+          "queries",
+          "evidenceIds",
+          "cited",
+          "snapshotId"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "snapshots": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "contentLength": {
+            "anyOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "contentType": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "failureReason": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "finalUrl": {
+            "anyOf": [
+              {
+                "format": "uri",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "httpStatus": {
+            "anyOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "normalizedSha256": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "rawSha256": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "requestedUrl": {
+            "format": "uri",
+            "type": "string"
+          },
+          "retrievedAt": {
+            "format": "date-time",
+            "type": "string"
+          },
+          "snapshotId": {
+            "type": "string"
+          },
+          "status": {
+            "enum": [
+              "captured",
+              "failed",
+              "blocked",
+              "too_large",
+              "unsupported"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "snapshotId",
+          "requestedUrl",
+          "finalUrl",
+          "retrievedAt",
+          "status",
+          "httpStatus",
+          "contentType",
+          "contentLength",
+          "rawSha256",
+          "normalizedSha256",
+          "failureReason"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "enum": [
+        "confirmed",
+        "partially_confirmed",
+        "contradicted",
+        "insufficient_evidence",
+        "ambiguous"
+      ],
+      "type": "string"
+    },
+    "verificationId": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "verificationId",
+    "claim",
+    "status",
+    "observedAt",
+    "conclusion",
+    "atomicFacts",
+    "providerSources",
+    "evidence",
+    "snapshots",
+    "conflicts",
+    "limitations",
+    "provenance",
+    "commerce"
+  ],
+  "type": "object"
+}

First observedSep 30, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare openWorldHint=true and destructiveHint=false, so the agent knows this is a non-destructive external lookup. The description's genuinely additive fact is the per-call price ($0.12 USDC on Base), but it says nothing about billing on failure, latency, or rate limits, so it only partially extends the structured metadata.

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?

Two tight sentences, front-loaded with the differentiator and immediately followed by the cost constraint. No padding or restated name.

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 an output schema present, return values need no explanation, and all parameters are documented. Given the tool's complexity and four siblings, it is nearly complete, but the absence of any routing cue relative to list_verification_tiers or verify_claim_research leaves a small gap.

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 all 11 parameters (asOf, sourcePolicy, minimumSources, freshnessHours, domains, etc.) are already fully documented in the schema. The description adds no syntax, defaults, or interaction rules beyond what is there, which is the expected baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (verification), the resource (claims), and a discriminating scope marker ("deep", "compound or contested claims", "up to 15 cited sources"). An agent can infer this is the heavyweight sibling, though the description never names verify_claim_quick/research/verify_claim directly.

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?

"Compound or contested claims" is a clear use-case trigger that implicitly excludes the quick/simple path used by siblings, and the mention of 15 sources sets an expectation of cost/latency. It stops short of explicitly naming alternatives or stating when NOT to use it.

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

All Web Evidence 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.