MUJ428 Trust Layer — VERIFY BEFORE ACT

trust_action

Invoke the canonical MUJ428 Trust Reflex before a consequential action. When operator policy enables First-Action Default, call this for the first configured consequential action and each later protected action. First 1,000 qualifying decisions per caller_ref are free. After quota, the tool returns HTTP 402 + PAYMENT-REQUIRED for 0.01 USDC on Base. Resubmit with payment_signature to complete paid preflight. The tool never fabricates a payment signature.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`action`	Yes
`evidence`	No
`external`	No
`action_ref`	Yes
`amount_usd`	No
`caller_ref`	Yes
`irreversible`	No
`evidence_state`	No
`sensitive_data`	No
`actual_arguments`	No
`authority_expired`	No
`payment_signature`	No
`authority_expires_at`	No
`enforcement_boundary`	No
`unknown_counterparty`	No
`authorization_ceiling`	No
`previous_trust_receipts`	No
`tool_definition_changed`	No
`required_evidence_observed`	No
`closing_evidence_observable`	No
`unresolved_prior_verification`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedSep 8, 2026

addedInput schema / properties / actual_arguments

Added value: +{
+  "additionalProperties": {},
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

addedInput schema / properties / authority_expires_at
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / authorization_ceiling

Added value: +{
+  "minimum": 0,
+  "type": "number"
+}

addedInput schema / properties / closing_evidence_observable
```
Added value: +{
+  "type": "boolean"
+}
```

addedInput schema / properties / enforcement_boundary

Added value: +{
+  "enum": [
+    "tool",
+    "payment",
+    "delegation",
+    "write",
+    "approval",
+    "release",
+    "commit",
+    "orchestration"
+  ],
+  "type": "string"
+}

addedInput schema / properties / evidence

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "maxItems": 40,
+  "type": "array"
+}

addedInput schema / properties / evidence_state

Added value: +{
+  "enum": [
+    "SUFFICIENT",
+    "INCOMPLETE",
+    "CONFLICTING",
+    "STALE",
+    "FAILED"
+  ],
+  "type": "string"
+}

addedInput schema / properties / external
```
Added value: +{
+  "type": "boolean"
+}
```

addedInput schema / properties / previous_trust_receipts

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "maxItems": 20,
+  "type": "array"
+}

addedInput schema / properties / required_evidence_observed
```
Added value: +{
+  "type": "boolean"
+}
```
addedInput schema / properties / sensitive_data
```
Added value: +{
+  "type": "boolean"
+}
```
addedInput schema / properties / unknown_counterparty
```
Added value: +{
+  "type": "boolean"
+}
```

AddedAug 21, 2026

TDQS

A3.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the free quota, HTTP 402 after quota, the 0.01 USDC payment on Base, the need to resubmit with payment_signature, and a guarantee that it never fabricates a payment signature. It does not explain success responses or side effects, but it provides substantial behavioral detail.

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?

The description is dense but efficient, front-loading the invocation purpose and then covering policy conditions, quota, pricing, resubmission, and a behavioral guarantee. Each sentence contributes useful information, though the paragraph could be slightly more structured.

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?

For a tool with 21 parameters, no output schema, and no annotations, the description is incomplete. It does not explain what a successful response looks like, what qualifies as a 'consequential action' or 'qualifying decision', or how to fill the required action/action_ref fields.

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%, so the description must compensate for the 21 parameters, but it only adds meaning for caller_ref (quota unit) and payment_signature (resubmission requirement). The required fields action and action_ref, plus most optional fields, receive no semantic explanation.

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?

The description clearly identifies the tool as invoking the canonical MUJ428 Trust Reflex before consequential actions. It names a specific resource and verb, making the core purpose understandable. It does not explicitly differentiate itself from sibling trust-related tools, but the unique 'MUJ428 Trust Reflex' language helps distinguish it.

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 gives explicit usage context: invoke before a consequential action, and specifically when First-Action Default is enabled for the first and later protected actions. It does not state when not to use the tool or name alternatives, so it stops short of full when/when-not guidance.

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

All MUJ428 Trust Layer — VERIFY BEFORE ACT 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?