agent-verified-relay

Call verified

call_verified

Relay a tools/call to a registered MCP service and notarize the exchange: request hash + response hash + outcome land in a tamper-evident receipt chain. Idempotent on call_id (a replay returns the original receipt and cached result — the downstream is never double-called). Failures are receipted evidence, not silence.

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": {
      "service_id": "<service_id>",
      "tool": "<tool>",
      "call_id": "<call_id>"
    },
    "name": "call_verified"
  }
}

Input Schema

Name	Required	Description	Default
`tool`	Yes
`call_id`	Yes
`arguments`	No
`timeout_s`	No
`request_id`	No
`service_id`	Yes
`payment_ref`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 24, 2026

addedInput schema / properties / request_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Request Id"
+}

Changed1 schema field changedJul 16, 2026

addedInput schema / properties / payment_ref

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Payment Ref"
+}

First observedJul 15, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description discloses substantial behavior: hash-based notarization into a tamper-evident chain, replay returning the cached result without a second downstream invocation, and failures being receipted rather than silent. It does not cover auth/permission needs at the downstream service or how timeout_s interacts with the receipt, but the side-effect and retry profile is well explained.

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?

Three tight sentences, front-loaded with the action, then the guarantee, then the failure contract. The parenthetical about replay is doing real work rather than restating the sentence, and there is no filler.

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

Completeness3/5

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

The relay/notarize contract is well conveyed and an output schema exists to carry return structure, so return values need not be described. But for a 7-parameter tool that relays arbitrary downstream calls and accepts a payment reference, the description leaves key operational questions (billing semantics, per-service auth, timeout behavior) unanswered.

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 0% across 7 parameters, so the description must compensate — and it only does so for one: call_id is clearly established as the idempotency key with defined replay semantics. service_id, tool, arguments, timeout_s, request_id, and payment_ref (notably the payment_ref, which implies a billing path) are given no meaning anywhere, leaving the caller to guess.

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 a precise verb pair — 'Relay a tools/call ... and notarize the exchange' — naming both the action and the durable artifact (receipt chain with request/response hashes). This is unmistakably distinct from siblings such as list_services (discovery), get_receipt (retrieval only), and verify_receipts (audit), so an agent can pick it without comparing schemas.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: 'a registered MCP service' hints that register_service must run first, and 'Idempotent on call_id' tells the agent how to safely retry. However, it never states when NOT to use this tool (e.g., for read-only inspection prefer get_receipt) nor names any sibling as an alternative.

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

All agent-verified-relay 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.