R/IV — Verify Claims, Citations & Agent Actions

agent.monitor

R/IV agent.monitor — independent evidence-verification primitive for monitoring. Completed paid execution returns an RVO plus signed R/IV Verification Receipt.

Input Schema

Name	Required	Description	Default
`target`	Yes
`cadence`	No		daily
`request_id`	Yes	Caller-generated idempotency key for this paid execution attempt.
`public_urls`	No
`materiality_rule`	No

Output Schema

Name	Required	Description
`cost`	Yes
`jobId`	Yes
`result`	Yes	R/IV Verification Object with evidence, limitations, verdict and resultHash.
`status`	Yes
`receipt`	Yes
`verdict`	Yes
`requestId`	Yes
`timestamps`	Yes
`operationId`	Yes
`schemaVersion`	Yes
`operationVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$id": "https://rdiv-production-runtime-production.up.railway.app/schemas/riv-machine-result-v2.json",
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": true,
+  "description": "Schema of a completed R/IV machine execution. Cryptographic receipt integrity does not independently establish the truth of any underlying conclusion. Free trials may use a separate contract.",
+  "properties": {
+    "cost": {
+      "additionalProperties": true,
+      "properties": {
+        "amount": {
+          "minimum": 0,
+          "type": "number"
+        },
+        "currency": {
+          "const": "USD"
+        }
+      },
+      "required": [
+        "currency",
+        "amount"
+      ],
+      "type": "object"
+    },
+    "jobId": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "operationId": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "operationVersion": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "receipt": {
+      "additionalProperties": true,
+      "properties": {
+        "issuedAt": {
+          "format": "date-time",
+          "type": "string"
+        },
+        "jobId": {
+          "type": "string"
+        },
+        "operationId": {
+          "type": "string"
+        },
+        "receiptId": {
+          "type": "string"
+        },
+        "receiptVersion": {
+          "type": "string"
+        },
+        "requestId": {
+          "type": "string"
+        },
+        "resultHash": {
+          "pattern": "^[a-f0-9]{64}$",
+          "type": "string"
+        },
+        "sha256": {
+          "pattern": "^[a-f0-9]{64}$",
+          "type": "string"
+        },
+        "signature": {
+          "pattern": "^[a-f0-9]{64}$",
+          "type": "string"
+        }
+      },
+      "required": [
+        "receiptVersion",
+        "receiptId",
+        "jobId",
+        "requestId",
+        "operationId",
+        "resultHash",
+        "issuedAt",
+        "sha256",
+        "signature"
+      ],
+      "type": "object"
+    },
+    "requestId": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "result": {
+      "additionalProperties": true,
+      "description": "R/IV Verification Object with evidence, limitations, verdict and resultHash.",
+      "properties": {
+        "limitations": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "operationId": {
+          "type": "string"
+        },
+        "resultHash": {
+          "pattern": "^[a-f0-9]{64}$",
+          "type": "string"
+        },
+        "verdict": {
+          "type": "string"
+        },
+        "verificationId": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "operationId",
+        "verificationId",
+        "verdict",
+        "limitations",
+        "resultHash"
+      ],
+      "type": "object"
+    },
+    "schemaVersion": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "status": {
+      "const": "COMPLETED"
+    },
+    "timestamps": {
+      "additionalProperties": true,
+      "properties": {
+        "completedAt": {
+          "format": "date-time",
+          "type": "string"
+        }
+      },
+      "required": [
+        "completedAt"
+      ],
+      "type": "object"
+    },
+    "verdict": {
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "schemaVersion",
+    "requestId",
+    "jobId",
+    "operationId",
+    "operationVersion",
+    "status",
+    "verdict",
+    "result",
+    "receipt",
+    "cost",
+    "timestamps"
+  ],
+  "title": "R/IV Machine Verification Result v2 - authenticated paid execution",
+  "type": "object",
+  "x-riv-receipt-policy": {
+    "integrity": "server-side HMAC verification required for v1 receipts",
+    "meaning": "signed provenance and execution integrity; not evidence that an underlying claim is true"
+  },
+  "x-riv-status": "public-contract-v2-live-machine-completed-only"
+}

Changed3 schema fields changedOct 8, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties

Added value: +{
+  "cadence": {
+    "default": "daily",
+    "enum": [
+      "daily",
+      "weekly"
+    ]
+  },
+  "materiality_rule": {
+    "maxLength": 10000,
+    "type": "string"
+  },
+  "public_urls": {
+    "items": {
+      "format": "uri",
+      "type": "string"
+    },
+    "maxItems": 50,
+    "type": "array"
+  },
+  "request_id": {
+    "description": "Caller-generated idempotency key for this paid execution attempt.",
+    "maxLength": 200,
+    "minLength": 8,
+    "type": "string"
+  },
+  "target": {
+    "maxLength": 20000,
+    "minLength": 3,
+    "type": "string"
+  }
+}

addedInput schema / required

Added value: +[
+  "target",
+  "request_id"
+]

First observedOct 6, 2026

TDQS

C2.7/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It does add two genuinely useful facts beyond structured fields: execution is paid, and a completed run returns an RVO plus a signed Verification Receipt. However it omits auth/permission requirements, rate limits, what actually gets verified, and what an incomplete or failed run produces.

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?

It is short, front-loaded, and free of padding, with the output guarantee placed second. The only weakness is heavy reliance on undefined internal jargon, though that is a clarity rather than a length problem.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but for a 5-parameter, 20%-coverage, annotation-free tool the description is too thin: it never explains the parameters, the monitoring semantics, or how it relates to the many sibling monitors. An agent would struggle to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is only 20%, so four of five parameters (target, cadence, public_urls, materiality_rule) are documented only by name and type. The description adds no meaning for any parameter and instead introduces undefined terms (RVO, R/IV Receipt) that map to nothing in the schema.

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

Purpose3/5

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

It states a general function ("independent evidence-verification primitive for monitoring") and names an output, but "monitoring" largely restates the tool name and "agent.monitor" is never differentiated from the many sibling monitors (evidence.monitor, claim.monitor, policy.monitor, vendor.monitor). Jargon like "RVO" and "R/IV" is left undefined, so the agent cannot tell what it actually monitors.

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

Usage Guidelines2/5

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

No indication of when this tool should be chosen over the numerous *monitor and *verify siblings, and no exclusions or prerequisites beyond the implicit "paid execution." The agent is left to infer selection criteria entirely.

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

All R/IV — Verify Claims, Citations & Agent Actions tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?