Skip to main content
Glama

Preflight before a cross-chain transfer: cost, arrival and saving (free, no signature)

recta_preflight
Read-only

Call before any cross-chain USDC/USDT transfer. Give the corridor and the amount (and, optionally, baseline_provider: the route you would use; without it Recta compares against lifi, LI.FI's own quote, or across where LI.FI does not apply). Returns, for your route, its estimated total cost in USDC and when it arrives; and, when Recta proves a cheaper route, the saving (a proven lower bound), Recta's 5 % fee, that route's total cost and arrival (the route itself is not named) and execute_via_recta: sign the same request to get the route. No wallet and no address needed (sender, recipient, constraints and gas ceilings are filled when absent and listed in assumed; your own sender gives the most exact figure). Stores nothing, charges nothing; 3 a day per IP address.

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": {
      "source_network": "<source_network>",
      "source_asset": "<source_asset>",
      "destination_network": "<destination_network>",
      "destination_asset": "<destination_asset>",
      "amount": "<amount>"
    },
    "name": "recta_preflight"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoAlternative to the fields above: the whole evaluation request body (from recta_request_template), as a JSON object.
amountYesHow much of source_asset to send, in whole tokens (not cents, not wei): "100" with USDC means 100 USDC. Minimum 3.5 for stablecoins (about 3.5 USD). No maximum.
senderNoOptional: your own sending address, for the most exact figure.
recipientNoOptional: the receiving address.
source_assetYesUppercase asset, e.g. USDC.
source_networkYesLowercase network as in the service descriptor, e.g. base, ethereum, arbitrum.
baseline_providerNoOptional: the route you would use without Recta, e.g. lifi, across, stargate_v2, cctp_v2_standard (recta_fit_check lists the ones a corridor admits). Absent: lifi, or across where LI.FI does not apply.
destination_assetYes
destination_networkYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / amount
      Added value: +{
      +  "description": "How much of source_asset to send, in whole tokens (not cents, not wei): \"100\" with USDC means 100 USDC. Minimum 3.5 for stablecoins (about 3.5 USD). No maximum.",
      +  "type": "string"
      +}
    • addedInput schema / properties / baseline_provider
      Added value: +{
      +  "description": "Optional: the route you would use without Recta, e.g. lifi, across, stargate_v2, cctp_v2_standard (recta_fit_check lists the ones a corridor admits). Absent: lifi, or across where LI.FI does not apply.",
      +  "type": "string"
      +}
    • changedInput schema / properties / body / description
      Previous value: -"The evaluation request body, as a JSON object or its JSON text."New value: +"Alternative to the fields above: the whole evaluation request body (from recta_request_template), as a JSON object."
    • changedInput schema / properties / body / type
      Previous value: -[
      -  "object",
      -  "string"
      -]New value: +"object"
    • addedInput schema / properties / destination_asset
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / destination_network
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / recipient
      Added value: +{
      +  "description": "Optional: the receiving address.",
      +  "type": "string"
      +}
    • addedInput schema / properties / sender
      Added value: +{
      +  "description": "Optional: your own sending address, for the most exact figure.",
      +  "type": "string"
      +}
    • addedInput schema / properties / source_asset
      Added value: +{
      +  "description": "Uppercase asset, e.g. USDC.",
      +  "type": "string"
      +}
    • addedInput schema / properties / source_network
      Added value: +{
      +  "description": "Lowercase network as in the service descriptor, e.g. base, ethereum, arbitrum.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "body"
      -]New value: +[
      +  "source_network",
      +  "source_asset",
      +  "destination_network",
      +  "destination_asset",
      +  "amount"
      +]
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint, the description discloses a great deal: no wallet or address required, absent fields are defaulted and listed in `assumed`, a 5% fee, the saving is a proven lower bound, the route is deliberately unnamed, nothing is stored or charged, and there is a 3-per-day-per-IP rate limit. These are the operationally important facts an agent needs and none of them live in the annotations.

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?

The call-to-action and the trigger condition are front-loaded, and every clause carries information. The return-value sentence is a long run-on with nested parentheses that takes effort to parse, which costs it a point, but there is no filler.

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 nine-parameter, nested-body, no-output-schema tool, the description covers the return shape (total cost, arrival, saving, fee, execute_via_recta), the defaulting behavior, and the rate limit. An agent can decide to call it and interpret the result without consulting anything else.

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 78%, so the schema carries most parameter meaning; the description still adds value by explaining that baseline_provider defaults to lifi (or across outside LI.FI's coverage) and that supplying your own sender yields the most exact figure. It does not restate amount or network formatting rules, which the schema already covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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: call before a USDC/USDT transfer to get estimated total cost, arrival time, and proven savings. It also distinguishes the evaluation step from the execution step via execute_via_recta ("sign the same request to get the route"), which effectively points at a sibling. It stops short of naming alternatives like recta_trial_evaluation or recta_fit_check, so it is not a full 5.

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?

"Call before any cross-chain USDC/USDT transfer" gives an explicit trigger condition, and baseline_provider semantics (default to lifi, or across where LI.FI does not apply) tell the agent how to configure a comparison. There is no explicit when-not-to-use or naming of the sibling preflight variants, so it is clear but not exhaustive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.