Skip to main content
Glama

x402-data-gateway

by io.github.epistemedeus

Evaluate Stateful Wallet Policy Conformance

stateful_wallet_policy_conformance

Evaluate safe standardized observations from wallet policies that track prior or concurrent requests. Use wallet_policy_conformance instead for one-request action shape, method, chain, token, recipient, amount, and function controls. This tool separately tests sequential cumulative limits, signed-but-unbroadcast accounting, ABI extraction, concurrent oversubscription, counter-reference failure, and application serialization. It accepts no credentials, counter values, wallet or resource IDs, signatures, transactions, or raw provider responses and does not run the provider tests itself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
networkYesNetwork identifier used by the tested stateful profile.
protocolYesPayment or execution protocol bound by the tested stateful profile.
providerYesWallet or delegated-signer provider name.
profileIdYesCaller-defined stateful policy profile identifier with no credential, wallet, or counter secret.
observationsYesUnique standardized stateful observations. Raw provider responses, signatures, transactions, counter values, credentials, wallet IDs, and resource IDs are rejected.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
productYes
profileYes
resultsYes
boundaryYes
completeYes
decisionYes
evaluatedAtYes
unsafeCasesYes
schemaVersionYes
inconclusiveCasesYes
strictBudgetPassedYes
applicationVerifiedYes
missingRequiredCasesYes
standardSchemaVersionYes
providerNativeVerifiedYes
providerNativeUnverifiedYes

Schema Changelog

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

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "applicationVerified": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "boundary": {
+      "additionalProperties": false,
+      "properties": {
+        "credentialsAccepted": {
+          "const": false,
+          "type": "boolean"
+        },
+        "signaturesVerified": {
+          "const": false,
+          "type": "boolean"
+        },
+        "statement": {
+          "type": "string"
+        },
+        "transactionBroadcast": {
+          "const": false,
+          "type": "boolean"
+        },
+        "walletAccessed": {
+          "const": false,
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "credentialsAccepted",
+        "walletAccessed",
+        "signaturesVerified",
+        "transactionBroadcast",
+        "statement"
+      ],
+      "type": "object"
+    },
+    "complete": {
+      "type": "boolean"
+    },
+    "decision": {
+      "enum": [
+        "conformant",
+        "partial",
+        "unsafe"
+      ],
+      "type": "string"
+    },
+    "evaluatedAt": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "inconclusiveCases": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "missingRequiredCases": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "product": {
+      "const": "samedaydesk-stateful-wallet-policy-conformance",
+      "type": "string"
+    },
+    "profile": {
+      "additionalProperties": false,
+      "properties": {
+        "network": {
+          "type": "string"
+        },
+        "profileId": {
+          "type": "string"
+        },
+        "protocol": {
+          "type": "string"
+        },
+        "provider": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "profileId",
+        "provider",
+        "network",
+        "protocol"
+      ],
+      "type": "object"
+    },
+    "providerNativeUnverified": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "providerNativeVerified": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "actual": {
+            "enum": [
+              "allowed",
+              "denied",
+              "error"
+            ],
+            "type": "string"
+          },
+          "applicationVerified": {
+            "type": "boolean"
+          },
+          "case": {
+            "enum": [
+              "first_within_cap",
+              "sequential_exceeds_cap",
+              "signed_unbroadcast_counts",
+              "unrecognized_calldata",
+              "concurrent_exceeds_cap",
+              "missing_counter_reference",
+              "application_serialized_concurrent_exceeds_cap"
+            ],
+            "type": "string"
+          },
+          "code": {
+            "pattern": "^[A-Za-z0-9][A-Za-z0-9._:/-]{0,63}$",
+            "type": "string"
+          },
+          "control": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "enforcementClass": {
+            "enum": [
+              "none",
+              "policy",
+              "application",
+              "validation",
+              "provider"
+            ],
+            "type": "string"
+          },
+          "expectationMet": {
+            "type": "boolean"
+          },
+          "expected": {
+            "enum": [
+              "allow",
+              "deny"
+            ],
+            "type": "string"
+          },
+          "finding": {
+            "enum": [
+              "expected_behavior",
+              "unsafe_allowed",
+              "expected_behavior_not_proven",
+              "denied_outside_policy_or_application_guard"
+            ],
+            "type": "string"
+          },
+          "providerNativeVerified": {
+            "type": "boolean"
+          },
+          "required": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "case",
+          "actual",
+          "enforcementClass",
+          "expected",
+          "control",
+          "required",
+          "expectationMet",
+          "providerNativeVerified",
+          "applicationVerified",
+          "finding"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "schemaVersion": {
+      "const": "samedaydesk.stateful-wallet-policy-conformance.v1",
+      "type": "string"
+    },
+    "standardSchemaVersion": {
+      "const": "agent-payment-policy.stateful-wallet-policy-observation-report.v1",
+      "type": "string"
+    },
+    "strictBudgetPassed": {
+      "type": "boolean"
+    },
+    "unsafeCases": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "schemaVersion",
+    "standardSchemaVersion",
+    "product",
+    "evaluatedAt",
+    "profile",
+    "decision",
+    "complete",
+    "strictBudgetPassed",
+    "results",
+    "providerNativeVerified",
+    "providerNativeUnverified",
+    "applicationVerified",
+    "missingRequiredCases",
+    "unsafeCases",
+    "inconclusiveCases",
+    "boundary"
+  ],
+  "type": "object"
+}
  2. Added

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does well by stating it 'accepts no credentials, counter values, wallet or resource IDs, signatures, transactions, or raw provider responses' and 'does not run the provider tests itself.' It does not explicitly state whether the operation is read-only or has side effects, but the evaluative framing and input restrictions strongly imply a safe, non-mutating test.

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 three sentences, front-loaded with the core purpose, then the alternative tool, then the distinguishing test scope and input constraints. Every sentence earns its place, and the structure is easy to scan.

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

Completeness5/5

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

For a tool with five required parameters, no annotations, and an output schema, the description is complete: it explains what the tool evaluates, how it differs from the sibling, what inputs are forbidden, and what it does not do. The output schema presumably covers return values, so no further return-format detail is needed.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful context by enumerating the tested behaviors (sequential cumulative limits, signed-but-unbroadcast accounting, ABI extraction, concurrent oversubscription, counter-reference failure, application serialization) that map to the observation `case` enum. It also reinforces the schema's rejection of unsafe inputs, adding value beyond the parameter descriptions.

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 opens with a specific verb and resource: 'Evaluate safe standardized observations from wallet policies that track prior or concurrent requests.' It clearly distinguishes this tool from its sibling by naming `wallet_policy_conformance` and contrasting the one-request controls it handles.

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

Usage Guidelines5/5

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

The description explicitly directs users to `wallet_policy_conformance` for one-request action shape, method, chain, token, recipient, amount, and function controls, while stating this tool is for stateful cumulative, concurrency, and serialization tests. This provides clear when-to-use and when-not-to-use guidance.

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

All x402-data-gateway toolsInspect
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

A4.1/5.0
Disambiguation3/5

Several tools cluster around the same domain: there are multiple audit tools, multiple preflight tools, multiple receipt/settlement tools, and two wallet-policy-conformance tools. The descriptions are carefully distinguished with 'use X instead' notes, but an agent would still need to read closely to separate `agent_discoverability_audit` from `agent_surface_budget_audit` and `seller_integrity_audit` from `payment_offer_preflight`.

Naming Consistency4/5

Most names follow a readable, snake_case pattern with a domain prefix or action stem, such as `morpho_position`, `transaction_receipt`, `wallet_enrich`, and `contract_qualified_search`. The convention is not fully uniform—`read`, `extract`, `scan`, and `schemaforge` are standalone verbs or compounds, and `agent_surface_budget_audit` is a much longer construction—but the style is consistent enough to navigate.

Tool Count3/5

22 tools is at the heavy end of a data-gateway scope, especially since they spread across x402 discovery, Morpho lending, web domain audits, wallet policy, and blockchain receipts. Each tool explains its existence, but the set feels broader than one central data-gateway concern.

Completeness4/5

The tools form a coherent read-only x402/agent-commerce lifecycle: catalog search, discoverability, surface/seller integrity, payment offer preflight, settlement proof, and transaction receipt verification. There are some peripheral tools that do not directly serve x402, and no payment or execution action exists, but the read-only audit gate is intentionally complete and lacks dead ends.

Resources