Agent Decision & Evidence Tools (MCP + x402)

Agent Transaction Guard

tx_preflight

Read-only

Read-only decision analysis before signing with five on-chain core checks: native balance/gas price, transaction-specific gas estimate, simulation with decoded revert reason, pending nonce gap and recipient bytecode/type. Token inputs add an optional ERC-20 balance and allowance check. Returns proceed, review or block with evidence, unknowns, limitations and safe next actions. Wallet sanctions screening is not included because official name lists cannot clear or identify a blockchain address. Missing evidence is never approval; there are no follow-up charges.

Input Schema

TableJSON Schema

Name	Required	Default
`to`	Yes
`data`	No	0x
`chain`	No	base
`token`	No
`amount`	No
`sender`	Yes
`spender`	No
`value_eth`	No	0

Output Schema

TableJSON Schema

Name	Required	Description
`to`	No
`gas`	No
`note`	No
`tool`	No
`chain`	No
`error`	No
`nonce`	No
`token`	No
`value`	No
`checks`	No
`sender`	No
`charged`	No	When present on an error, false means the failed result is uncharged.
`message`	No
`missing`	No
`pricing`	No
`receipt`	No
`settled`	No	When present on an error, false means no settlement occurred.
`unknown`	No
`verdict`	No
`accepted`	No
`chain_id`	No
`contract`	No
`decision`	No
`evidence`	No
`read_only`	No
`recipient`	No
`retryable`	No
`checked_at`	No
`error_code`	No
`extensions`	No
`simulation`	No
`limitations`	No
`status_code`	No
`did_you_mean`	No
`next_actions`	No
`would_succeed`	No
`missing_checks`	No
`review_reasons`	No
`blocking_reasons`	No
`partial_evidence`	No
`wallet_sanctions`	No
`broadcasts_transaction`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedSep 6, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
changedInput schema / properties / amount / default
```
Previous value: -0New value: +""
```
removedInput schema / properties / amount / title
```
Removed value: -"Amount"
```

changedInput schema / properties / amount / type

Previous value: -"number"New value: +"string"

removedInput schema / properties / chain / title
```
Removed value: -"Chain"
```
removedInput schema / properties / data / title
```
Removed value: -"Data"
```
addedInput schema / properties / sender / pattern
```
Added value: +"^0x[a-fA-F0-9]{40}$"
```
removedInput schema / properties / sender / title
```
Removed value: -"Sender"
```
removedInput schema / properties / spender / title
```
Removed value: -"Spender"
```
addedInput schema / properties / to / pattern
```
Added value: +"^0x[a-fA-F0-9]{40}$"
```
removedInput schema / properties / to / title
```
Removed value: -"To"
```
removedInput schema / properties / token / title
```
Removed value: -"Token"
```
changedInput schema / properties / value_eth / default
```
Previous value: -0New value: +"0"
```
removedInput schema / properties / value_eth / title
```
Removed value: -"Value Eth"
```
changedInput schema / properties / value_eth / type
```
Previous value: -"number"New value: +"string"
```

removedInput schema / title

Removed value: -"tx_preflight_toolArguments"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "anyOf": [
+    {
+      "required": [
+        "contract",
+        "chain",
+        "chain_id",
+        "sender",
+        "to",
+        "value",
+        "checked_at",
+        "read_only",
+        "broadcasts_transaction",
+        "gas",
+        "simulation",
+        "nonce",
+        "recipient",
+        "wallet_sanctions",
+        "evidence",
+        "missing_checks",
+        "checks",
+        "decision",
+        "next_actions",
+        "would_succeed",
+        "blocking_reasons",
+        "review_reasons",
+        "verdict",
+        "pricing",
+        "limitations",
+        "note",
+        "receipt",
+        "extensions"
+      ]
+    },
+    {
+      "required": [
+        "error"
+      ]
+    }
+  ],
+  "description": "Structured result contract for tx_preflight. A success satisfies the documented success branch. A domain or tool error includes error and is not a successful settlement; unpaid x402 requirements are carried by the transport wrapper.",
+  "properties": {
+    "accepted": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "blocking_reasons": {
+      "items": {},
+      "type": "array"
+    },
+    "broadcasts_transaction": {
+      "type": "boolean"
+    },
+    "chain": {
+      "type": "string"
+    },
+    "chain_id": {
+      "type": "integer"
+    },
+    "charged": {
+      "description": "When present on an error, false means the failed result is uncharged.",
+      "type": "boolean"
+    },
+    "checked_at": {
+      "type": "string"
+    },
+    "checks": {
+      "items": {},
+      "type": "array"
+    },
+    "contract": {
+      "type": "string"
+    },
+    "decision": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "did_you_mean": {
+      "additionalProperties": true,
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "error": {
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "additionalProperties": true,
+          "properties": {
+            "code": {
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "message": {
+              "type": "string"
+            },
+            "param": {
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "type": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "message"
+          ],
+          "type": "object"
+        }
+      ]
+    },
+    "error_code": {
+      "type": "string"
+    },
+    "evidence": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "extensions": {
+      "additionalProperties": true,
+      "properties": {
+        "delivery-receipt": {
+          "additionalProperties": true,
+          "properties": {
+            "how_to_verify": {
+              "type": "string"
+            },
+            "issued_at": {
+              "format": "date-time",
+              "type": "string"
+            },
+            "issuer": {
+              "type": "string"
+            },
+            "issuer_key": {
+              "type": "string"
+            },
+            "key_id": {
+              "type": "string"
+            },
+            "result_hash": {
+              "type": "string"
+            },
+            "service": {
+              "type": "string"
+            },
+            "signature": {
+              "type": "string"
+            },
+            "signed_message": {
+              "type": "string"
+            },
+            "standard": {
+              "const": "eucompliance-receipt/2",
+              "type": "string"
+            },
+            "subject": {
+              "type": "string"
+            },
+            "valid_until": {
+              "format": "date-time",
+              "type": "string"
+            },
+            "verify_url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "standard",
+            "service",
+            "subject",
+            "result_hash",
+            "issued_at",
+            "valid_until",
+            "issuer",
+            "issuer_key",
+            "key_id",
+            "verify_url",
+            "how_to_verify",
+            "signature",
+            "signed_message"
+          ],
+          "type": "object"
+        }
+      },
+      "required": [
+        "delivery-receipt"
+      ],
+      "type": "object"
+    },
+    "gas": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "limitations": {
+      "items": {},
+      "type": "array"
+    },
+    "message": {
+      "type": "string"
+    },
+    "missing": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "missing_checks": {
+      "items": {},
+      "type": "array"
+    },
+    "next_actions": {
+      "items": {},
+      "type": "array"
+    },
+    "nonce": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "note": {
+      "type": "string"
+    },
+    "partial_evidence": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "pricing": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "read_only": {
+      "type": "boolean"
+    },
+    "receipt": {
+      "additionalProperties": true,
+      "properties": {
+        "how_to_verify": {
+          "type": "string"
+        },
+        "issued_at": {
+          "format": "date-time",
+          "type": "string"
+        },
+        "issuer": {
+          "type": "string"
+        },
+        "issuer_key": {
+          "type": "string"
+        },
+        "key_id": {
+          "type": "string"
+        },
+        "result_hash": {
+          "type": "string"
+        },
+        "service": {
+          "type": "string"
+        },
+        "signature": {
+          "type": "string"
+        },
+        "signed_message": {
+          "type": "string"
+        },
+        "standard": {
+          "const": "eucompliance-receipt/2",
+          "type": "string"
+        },
+        "subject": {
+          "type": "string"
+        },
+        "valid_until": {
+          "format": "date-time",
+          "type": "string"
+        },
+        "verify_url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "standard",
+        "service",
+        "subject",
+        "result_hash",
+        "issued_at",
+        "valid_until",
+        "issuer",
+        "issuer_key",
+        "key_id",
+        "verify_url",
+        "how_to_verify",
+        "signature",
+        "signed_message"
+      ],
+      "type": "object"
+    },
+    "recipient": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "retryable": {
+      "type": "boolean"
+    },
+    "review_reasons": {
+      "items": {},
+      "type": "array"
+    },
+    "sender": {
+      "type": "string"
+    },
+    "settled": {
+      "description": "When present on an error, false means no settlement occurred.",
+      "type": "boolean"
+    },
+    "simulation": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "status_code": {
+      "type": "integer"
+    },
+    "to": {
+      "type": "string"
+    },
+    "token": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "tool": {
+      "type": "string"
+    },
+    "unknown": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "value": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "verdict": {
+      "type": "string"
+    },
+    "wallet_sanctions": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "would_succeed": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

AddedAug 3, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description reinforces them with 'Read-only'. It goes further by disclosing the output shape (proceed/review/block with evidence, unknowns, limitations, safe next actions), the sanctions limitation, the principle that missing evidence is never approval, and the absence of follow-up charges. This is exemplary transparency beyond what annotations provide.

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?

Every sentence earns its place: scope, check list, return behavior, explicit exclusion, and a safety caveat. The key behavioral facts are front-loaded, and the description is dense without being bloated.

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

Completeness4/5

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

The output schema covers return-value structure, and the description supplies decision semantics, limitations, and safe next actions. The main gap is parameter-level guidance for several of the eight inputs, which prevents a perfect score but still leaves the tool adequately specified.

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. It explains that 'Token inputs add an optional ERC-20 balance and allowance check', which partially covers token, amount, and spender. However, it does not clarify sender, to, data, chain, or value_eth, nor does it map the five core checks to specific parameters, leaving significant semantic gaps.

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 action ('Read-only decision analysis before signing'), names the resource (a transaction preflight), and enumerates five concrete on-chain checks. This clearly differentiates it from siblings such as gas_estimate, tx_status, or contract_info without requiring schema inspection.

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?

It clearly scopes the tool to pre-signing decision analysis and explicitly states what is not covered ('Wallet sanctions screening is not included'), with reasoning. It does not enumerate which sibling to use instead in most cases, but the context is strong enough for an agent to select this tool over simpler read-only utilities.

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

All Agent Decision & Evidence Tools (MCP + x402) 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.