Skip to main content
Glama
Sign In

Recta

by io.github.RectaBuild
OverviewDiscussionsAdmin

The whole evaluation request for my transfer (free, no signature)

recta_request_template
Read-only

Returns the full body of the evaluation request for a corridor, an amount and the route you would use anyway (baseline_provider): you fill only your sender, recipient and gas ceilings, then sign it with recta_prepare_signed_request and recta_send_signed_request.

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>",
      "baseline_provider": "<baseline_provider>"
    },
    "name": "recta_request_template"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountYesDecimal amount of the source asset, e.g. 100.
source_assetYesUppercase asset, e.g. USDC.
latency_classNo
source_networkYesLowercase network as in the service descriptor, e.g. base, ethereum, arbitrum.
guarantee_classNo
baseline_providerYesThe route you would use without Recta (see recta_fit_check's declarable_baselines).
destination_assetYes
destination_networkYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

The description reinforces the annotations by flagging the call as 'free, no signature', consistent with readOnlyHint=true, so no contradiction. It also discloses that the output is a body you later sign, which is useful behavioral context. It does not say whether the template contains placeholders, how the ceilings are filled in, or what the returned payload looks like.

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?

One sentence with the return value front-loaded, then the follow-up steps. Dense but every clause carries information. The sender/recipient/ceilings fragment is the one piece that adds confusion rather than value.

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

Completeness3/5

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

For an 8-parameter, 6-required tool with no output schema, the description explains the purpose and next steps but not the shape of the returned request body or what the optional latency_class and guarantee_class do. An agent can find the tool but may need to guess at part of the payload it will receive.

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 coverage is 50%, so the description must add meaning. It does clarify that baseline_provider is 'the route you would use anyway' and ties it back to recta_fit_check, but latency_class, guarantee_class and destination_asset/destination_network receive no explanation anywhere. The mention of filling 'sender, recipient and gas ceilings' has no matching parameters and risks misleading the agent about required inputs.

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?

States a specific verb and resource: 'Returns the full body of the evaluation request' for a corridor, amount and baseline_provider. It is distinguishable from recta_prepare_signed_request and recta_send_signed_request, which it explicitly names as the subsequent steps. It stops short of 5 because the 'you fill only your sender, recipient and gas ceilings' clause describes fields that are not in the input schema, blurring what this tool actually consumes.

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?

Gives clear sequencing: call this first to get the template, then sign with recta_prepare_signed_request and send with recta_send_signed_request. That routes the agent through the workflow well. It does not state when NOT to use it or how it relates to recta_fit_check beyond the baseline_provider reference.

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

All Recta toolsInspect
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.

Resources