DLL Execution

Base transaction simulation / Preflight

preflight_transaction

Read-only

Before signing: simulate one unsigned Base Mainnet (8453) candidate (chain_id/from/to/value/data); inspect call success/revert, top-level destination and L2 fee constraints, Judgment, reason codes and evidence. Free; no API key, wallet or payment. Complete supported EIP-1559 fee_estimation context optionally estimates L1/L2/applicable Operator/Total Network Fee separately; legacy Judgment is unchanged, not automatic PASS. Inspect http_status, response.judgment and response.simulation. After broadcast use verify_transaction. No signing, broadcasting, custody, asset-delta/risk scan or execution guarantee.

Input Schema

Name	Required	Description
`candidate`	Yes
`constraints`	No
`fee_estimation`	No	Explicit opt-in to a separate versioned network_fee_estimate. Missing transaction fields are never guessed. Legacy cost_estimate, Judgment and L2 constraints remain unchanged.

Output Schema

Name	Required	Description	Default
`response`	Yes
`http_status`	Yes
`retry_after_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026

addedInput schema / properties / fee_estimation

Added value: +{
+  "additionalProperties": false,
+  "description": "Explicit opt-in to a separate versioned network_fee_estimate. Missing transaction fields are never guessed. Legacy cost_estimate, Judgment and L2 constraints remain unchanged.",
+  "properties": {
+    "transaction": {
+      "additionalProperties": false,
+      "properties": {
+        "access_list": {
+          "additionalItems": false,
+          "description": "Only an empty access list is supported by this fee-estimate version.",
+          "items": [],
+          "maxItems": 0,
+          "type": "array"
+        },
+        "gas_limit": {
+          "description": "Declared gas limit, 21000–5000000. Original simulation ceiling is unchanged.",
+          "maxLength": 7,
+          "pattern": "^(0|[1-9][0-9]*)$",
+          "type": "string"
+        },
+        "max_fee_per_gas": {
+          "maxLength": 78,
+          "pattern": "^(0|[1-9][0-9]*)$",
+          "type": "string"
+        },
+        "max_priority_fee_per_gas": {
+          "maxLength": 78,
+          "pattern": "^(0|[1-9][0-9]*)$",
+          "type": "string"
+        },
+        "nonce": {
+          "description": "Explicit nonce, 0–9007199254740991; not checked against account state.",
+          "maxLength": 16,
+          "pattern": "^(0|[1-9][0-9]*)$",
+          "type": "string"
+        },
+        "type": {
+          "const": "eip1559",
+          "type": "string"
+        }
+      },
+      "required": [
+        "type",
+        "nonce",
+        "gas_limit",
+        "max_fee_per_gas",
+        "max_priority_fee_per_gas",
+        "access_list"
+      ],
+      "type": "object"
+    },
+    "version": {
+      "const": "base_network_fee_v1",
+      "type": "string"
+    }
+  },
+  "required": [
+    "version"
+  ],
+  "type": "object"
+}

First observedOct 13, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Adds real context beyond the annotations: no cost, no API key/wallet/payment, and an explicit boundary list (no signing, broadcasting, custody, asset-delta/risk scan, or execution guarantee). It also warns that legacy Judgment stays unchanged and is not an automatic PASS. It does not contradict readOnlyHint=true; the only gap is no detail on latency or rate limits.

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?

Front-loaded with the trigger ('Before signing'), and the dense single paragraph carries a lot of load-bearing information. Slight redundancy appears in the repeated capability-boundary statements (free/no key vs no signing/custody) and the twice-mentioned Judgment, which keeps it from a 5.

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 complex nested-schema tool with an output schema present, the description covers the prerequisites (free, no key), the optional fee path, where to read results (http_status, response.judgment, response.simulation), and the hand-off to verify_transaction. Nothing needed to call it correctly is missing.

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?

Over a low 33% schema-description coverage, the prose still explains the candidate tuple (chain_id/from/to/value/data), that constraints are L2 fee/destination constraints, and that fee_estimation is an opt-in EIP-1559 context that reports L1/L2/Operator/Total fees separately. It does not disambiguate denied_to vs allowed_to, but adds meaningful semantic framing the schema lacks.

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?

States a specific verb+resource (simulate one unsigned Base Mainnet candidate) and enumerates what is inspected: call success/revert, destination, L2 fee constraints, Judgment, reason codes and evidence. It also explicitly separates itself from the sibling by noting verify_transaction is the post-broadcast tool.

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?

Gives a precise when-to-use trigger ('Before signing') and names the alternative plus its condition ('After broadcast use verify_transaction'). It also scopes optionality ('fee_estimation ... optionally') so the agent knows the fee block is not required.

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

All DLL Execution 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.