Skip to main content
Glama

Veriql preflight (one call before send, swap or sign)

veriql_preflight

Check a transaction's recipient for sanctions and freezes, simulate USDT transfers, score tokens, and decode signatures to return ALLOW, WARN, or BLOCK before sending.

Instructions

Every check one transaction needs, in one call, on whatever you pass: the recipient screen (OFAC, Drain Watch, Tether and Circle freezes) on to, the USDT transfer simulation when from and to are both on Tron or both on Ethereum, the launch score on tokenAddress, and the signature decode on calldata or typedData. Answers ALLOW, WARN or BLOCK. BLOCK only on a fact that loses money; a low score alone is WARN.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "veriql_preflight"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoRecipient address
fromNoSending address, for the USDT transfer simulation
amountNoUSDT amount, like 250; leave out to check the whole balance
chainIdNoChain id or key (1, ethereum, base, tron, solana); read off the addresses when omitted
calldataNoCalldata or a JSON-RPC request to decode
typedDataNoEIP-712 typed data, as JSON
tokenAddressNoToken to score before buying or swapping

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does useful work: it discloses the verdict taxonomy (ALLOW/WARN/BLOCK) and, critically, the decision rule — BLOCK only on a fact that loses money, a low score alone is WARN. It does not state auth/cost/rate-limit behavior or whether a call is purely read-only, so a small gap remains.

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?

Two sentences, both earning their place, with the verdict semantics placed last as a qualifier on the checks. The first sentence is a dense run-on that packs four conditional checks together, which slightly slows parsing but wastes no words.

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?

There is no output schema, so the description correctly supplies the return contract (ALLOW/WARN/BLOCK plus the rule behind BLOCK). All seven parameters are optional and documented, and conditional logic is covered; what is missing is behavior when no meaningful parameters are passed and any indication of latency/cost for a multi-check call.

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; the description goes beyond it by explaining conditional activation — the USDT transfer simulation only fires when `from` and `to` are both on Tron or both on Ethereum — which the schema does not express. It also ties each parameter to a distinct downstream check, adding interpretive value.

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 capability — running every needed check on a transaction in one call — and enumerates which check runs on which input (`to` screening, USDT simulation for the Tron/Ethereum pair, `tokenAddress` launch score, `calldata`/`typedData` signature decode). An agent can tell this is the aggregate preflight versus the single-purpose siblings like veriql_freeze or veriql_signature.

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 title and opening phrase 'one call before send, swap or sign' give a clear usage context, and 'on whatever you pass' implies checks are selected by the inputs supplied. It stops short of naming alternatives or stating when NOT to use it (e.g. when you only need one check, use the single-purpose sibling).

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