Skip to main content
Glama

Check a send to Canton (Before-you-send checklist)

gateway_preflight
Read-only

Validate a Zenith EVM-to-Canton transfer against every pre-send rule, dry-run the exact transaction, and return pass/fail checks, fixes, arrival amount, and unsigned tx without sending.

Instructions

Runs every rule in Zenith's "Before you send" checklist for a transfer from Zenith EVM to a Canton party, then dry-runs the exact transaction against the network (eth_estimateGas) to surface its own refusal reason. Returns pass/fail per check with fixes, the amount that arrives on Canton, and the unsigned transaction. Never sends anything. ALWAYS call this before sending to a Canton party.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "partyId": "<partyId>",
      "token": "<token>",
      "amount": "<amount>"
    },
    "name": "gateway_preflight"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoSender address; enables the balance check and the live dry run
tokenYesToken: "ZTH", a symbol (e.g. DevUSD, DORIG), a Canton instrument ID or an ERC-20 address
amountYesAmount, e.g. "0.5"
partyIdYesFull Canton party ID: hint::1220 followed by 64 hex digits
amountUnitNotoken = whole tokens (default); base = EVM base units / weitoken

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

The description adds substantial behavior beyond the annotations: it discloses that it runs checklist rules, performs a live eth_estimateGas dry run, surfaces refusal reasons, returns fixes, computes the Canton arrival amount, and never sends. These details align with readOnlyHint and openWorldHint and give an agent a realistic model of what happens.

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 front-loaded and efficient: it states what the tool does, how it behaves, what it returns, and the key safety property, then closes with the mandatory usage instruction. There is no unnecessary wording.

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 multi-check preflight/dry-run tool with no output schema, the description explains enough about returns and behavior: pass/fail per check with fixes, the Canton arrival amount, and the unsigned transaction. It also makes the non-sending guarantee explicit, which is the critical safety context for this tool.

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

Parameters3/5

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

Schema description coverage is 100%, and the schema already documents each parameter including the from, token, amount, partyId, and amountUnit fields. The description reinforces the EVM-to-Canton direction but does not add parameter-level syntax or constraints beyond the schema.

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 uses specific verbs and resources: it runs Zenith's Before-you-send checklist, dry-runs the transaction via eth_estimateGas, and returns per-check results plus an unsigned transaction. It clearly distinguishes itself from a sending tool by stating it never sends anything and should be called before sending to a Canton party.

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 gives strong usage guidance with 'ALWAYS call this before sending to a Canton party,' making the intended timing explicit. It does not state when not to use it or name a specific alternative for non-Canton transfers, but the core guidance is clear.

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