Skip to main content
Glama
Sign In

Mercadopleis

by io.github.castiquark
OverviewDiscussionsAdmin

create_order

Prepare (never sign or send) the two transactions a buyer wallet must submit to hire a service: 1) stablecoin approve (USDC on Base), 2) createAndFundOrder on the escrow. Non-custodial: this server holds no keys. Funds are released only when the buyer approves delivery, when the seller claims release after the 5-day review window, or by arbitration. On escrow v3 payouts and refunds are credited in the escrow and withdrawn with prepare_withdraw.

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": {
      "serviceId": "<serviceId>",
      "buyerWallet": "<buyerWallet>"
    },
    "name": "create_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
chainIdNo8453 Base Mainnet (default) or 84532 Base Sepolia with free test USDC
serviceIdYesService slug or UUID
buyerWalletYesAddress of the wallet that will fund the escrow

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
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 delivers: it explicitly says it never signs or sends, that the server holds no keys, and it spells out the three fund-release paths plus the 5-day review window. It does not describe the prepared output shape or error conditions, which keeps it below 5.

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?

Purpose and the two prepared transactions are front-loaded, then safety and release conditions follow in a logical order. It is dense but each sentence carries real information; the escrow v3 payout note is slightly tangential but still earns its place as context.

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?

For a fund-moving prepare tool with no annotations and no output schema, the description covers what matters most: what it prepares, that it is non-custodial, and when funds move. It could say more about what the caller receives back and any auth prerequisite, but the critical context is present.

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 100%, so the schema already documents chainId, serviceId and buyerWallet in detail. The description adds nothing about parameter syntax or defaults beyond what the schema says (e.g. USDC on Base, which mirrors the chainId description). Baseline 3 is appropriate.

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 names a concrete verb and resource: prepare the two transactions (USDC approve + createAndFundOrder on escrow) a buyer submits to hire a service. That is specific and distinguishes it from read-only siblings. It stops short of naming the nearest sibling, register_order, so an agent cannot tell them apart from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'to hire a service', which is enough to know the general situation. There is no explicit when-not or alternative routing, and the sibling register_order is never mentioned, so an agent must infer which of the two to call. The reference to prepare_withdraw covers downstream payouts, not tool selection here.

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

All Mercadopleis 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