RunOnProof

release_payment_to_supplier

Read-onlyIdempotent

Paid RunOnProof Payment Decision: one US FEDERAL_ONLY release-payment decision for 0.79 USDC on Base, with signed BuyerPaymentMandate, signed Proof Capsule and deterministic replay. RunOnProof does not execute supplier payment.

Input Schema

TableJSON Schema

Name	Required	Description
`buyer`	Yes
`payee`	Yes
`amount`	Yes
`intent`	Yes
`invoice`	Yes
`coverage`	Yes
`currency`	Yes
`supplier`	Yes
`disclosure`	Yes
`correlation`	Yes
`risk_policy`	Yes
`jurisdiction`	Yes
`buyer_mandate`	Yes	Signed BuyerPaymentMandate bound to this request digest, buyer, agent, supplier, payee, limits and validity window.
`schema_version`	Yes
`idempotency_key`	Yes
`economic_purpose`	Yes
`requesting_agent`	Yes
`decision_fee_payer`	No	Decision fee wallet authorized by the signed request and buyer mandate; required for commercial x402 purchases.
`evidence_references`	Yes
`payment_destination`	Yes
`coverage_requirements`	Yes
`freshness_requirements`	Yes
`exposure_valuation_basis`	Yes
`payment_instruction_digest`	Yes
`payment_exposure_usdc_equivalent_atomic`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`policy`	Yes
`replay`	Yes
`billing`	Yes
`product`	Yes
`coverage`	Yes
`decision`	Yes
`delivery`	Yes
`freshness`	Yes
`conditions`	Yes
`request_id`	Yes
`decision_id`	Yes
`remediation`	Yes
`uncertainty`	Yes
`valid_as_of`	Yes
`valid_until`	Yes
`reason_codes`	Yes
`risk_signals`	Yes
`checks_waived`	Yes
`decision_cost`	Yes
`economic_risk`	Yes
`proof_capsule`	Yes
`machine_action`	Yes
`request_digest`	Yes
`schema_version`	Yes
`checks_executed`	Yes
`evidence_bundle`	Yes
`product_version`	Yes
`payment_executed`	Yes
`decision_request_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedSep 6, 2026

addedInput schema / properties / decision_fee_payer

Added value: +{
+  "description": "Decision fee wallet authorized by the signed request and buyer mandate; required for commercial x402 purchases.",
+  "pattern": "^0x[0-9a-fA-F]{40}$",
+  "type": "string"
+}

Changed5 schema fields changedSep 4, 2026

addedInput schema / properties / buyer_mandate / properties / payload / additionalProperties
```
Added value: +false
```

addedInput schema / properties / buyer_mandate / properties / payload / properties

Added value: +{
+  "buyer_organization": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "buyer_organization_digest": {
+    "pattern": "^sha256:[0-9a-f]{64}$",
+    "type": "string"
+  },
+  "currency": {
+    "pattern": "^[A-Z]{3}$",
+    "type": "string"
+  },
+  "issuer": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "key_id": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "mandate_id": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "mandate_version": {
+    "pattern": "^\\d+\\.\\d+\\.\\d+$",
+    "type": "string"
+  },
+  "max_decision_fee_atomic": {
+    "pattern": "^\\d+$",
+    "type": "string"
+  },
+  "max_payment_amount": {
+    "pattern": "^(0|[1-9][0-9]{0,17})(\\.[0-9]{1,6})?$",
+    "type": "string"
+  },
+  "nonce": {
+    "maxLength": 96,
+    "minLength": 16,
+    "pattern": "^[A-Za-z0-9_-]+$",
+    "type": "string"
+  },
+  "payee_fingerprint": {
+    "pattern": "^sha256:[0-9a-f]{64}$",
+    "type": "string"
+  },
+  "permitted_intent": {
+    "const": "RELEASE_PAYMENT_TO_SUPPLIER"
+  },
+  "request_digest": {
+    "pattern": "^sha256:[0-9a-f]{64}$",
+    "type": "string"
+  },
+  "revocation_reference": {
+    "maxLength": 512,
+    "minLength": 1,
+    "type": "string"
+  },
+  "schema_version": {
+    "const": "1.0.0"
+  },
+  "subject_agent_id": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "supplier_entity_id": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "valid_from": {
+    "format": "date-time",
+    "type": "string"
+  },
+  "valid_until": {
+    "format": "date-time",
+    "type": "string"
+  }
+}

addedInput schema / properties / buyer_mandate / properties / payload / required

Added value: +[
+  "schema_version",
+  "mandate_id",
+  "mandate_version",
+  "issuer",
+  "subject_agent_id",
+  "buyer_organization",
+  "buyer_organization_digest",
+  "permitted_intent",
+  "request_digest",
+  "supplier_entity_id",
+  "payee_fingerprint",
+  "max_payment_amount",
+  "currency",
+  "max_decision_fee_atomic",
+  "valid_from",
+  "valid_until",
+  "nonce",
+  "key_id",
+  "revocation_reference"
+]

addedInput schema / properties / buyer_mandate / properties / signature / additionalProperties
```
Added value: +false
```

addedInput schema / properties / buyer_mandate / properties / signature / properties

Added value: +{
+  "algorithm": {
+    "const": "Ed25519"
+  },
+  "canonicalization": {
+    "const": "ROP-C14N-JSON-1"
+  },
+  "issuer": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "key_id": {
+    "maxLength": 160,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]*$",
+    "type": "string"
+  },
+  "value": {
+    "pattern": "^[A-Za-z0-9_-]{86}$",
+    "type": "string"
+  }
+}

AddedSep 2, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false; the description adds useful behavioral detail by stating deterministic replay and explicitly disclaiming execution of supplier payment. It does not mention fees, internal state changes, or response semantics, but the added caveats meaningfully extend the annotation baseline.

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 compact sentences with no filler. It front-loads the most decision-relevant constraints and ends with the critical non-execution caveat, making every word count.

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?

Despite having annotations and an output schema, the description is far too thin for a 25-parameter, deeply nested tool with only 8% schema coverage. It does not explain how to assemble or obtain the signed BuyerPaymentMandate and Proof Capsule, what Base means in terms of payment_destination, or how to populate the 24 required fields, so an agent cannot reliably invoke it from the description alone.

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?

With only 8% schema description coverage and 25 required parameters, the description needed to compensate by explaining how to populate key fields, but it only hints at a few concepts: US, FEDERAL_ONLY, 0.79 USDC, Base, signed BuyerPaymentMandate, and signed Proof Capsule. The deeply nested buyer_mandate, requesting_agent, risk_policy, correlation, and coverage_requirements objects remain essentially undocumented, leaving an agent with insufficient guidance for constructing a valid request.

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 states a specific action: it returns one paid RunOnProof payment decision for a US FEDERAL_ONLY release-payment of 0.79 USDC on Base, with a signed BuyerPaymentMandate, signed Proof Capsule, and deterministic replay. It also explicitly says RunOnProof does not execute supplier payment, which clearly separates this decision tool from payment-execution tools.

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 clear context: this is a one-time, paid, deterministic decision for a specific US FEDERAL_ONLY payment, and it explicitly notes that supplier payment is not executed. However, it does not name sibling alternatives such as preflight, quote, or resolve_agent_intent, nor does it state when to prefer this tool over them.

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

All RunOnProof tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0

Disambiguation4/5

Most tools target distinct artifacts or workflow stages: capability listing, quoting, preflighting, payment decisions, and verification. The closest overlap is between get_agent_first_portfolio and resolve_agent_intent, and between capabilities and quote, but the descriptions provide enough differentiation to avoid frequent misselection.

Naming Consistency3/5

Several tools follow a verb_noun pattern (resolve_agent_intent, release_payment_to_supplier, verify_passport, verify_receipt), while others are bare nouns or single words (capabilities, preflight, quote). The style is readable and consistently lowercase snake_case, but the lack of a uniform verb convention makes the set feel inconsistent.

Tool Count5/5

Eight tools is well within the ideal range and maps cleanly to the main phases of the service: discover, quote, decide, release, and verify. No tool feels redundant enough to remove, and none suggest an overgrown surface.

Completeness4/5

The set covers the core lifecycle from capability discovery and intent resolution through preflight, quoting, release decisions, and post-decision verification. Minor gaps exist such as no history/list decisions or payment execution, but those may be intentionally outside the server's scope.

Resources

Need Help?