Skip to main content
Glama

Prepare an unsigned buyer-started deal

prepare_deal
Read-only

Builds two unsigned transactions for a buyer-started USDC escrow deal: a USDC approve and proposeDeal. Returns calldata only; does not sign, store, or broadcast, and rejects paused or closed funding.

Instructions

Build two unsigned transactions for a buyer-started deal: a USDC approve and proposeDeal. Returns calldata only. Does not store the manifest, does not hold a key, does not sign, and does not broadcast. Refuses when funding is paused or closed.

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": {
      "buyer": "<buyer>",
      "seller": "<seller>",
      "amount_usdc": "<amount_usdc>",
      "mode": "<mode>",
      "fallback_seller_bps": "<fallback_seller_bps>",
      "acceptance_window": "<acceptance_window>",
      "delivery_window": "<delivery_window>",
      "decision_window": "<decision_window>",
      "arbitration_window": "<arbitration_window>",
      "manifest": "<manifest>"
    },
    "name": "prepare_deal"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
saltNoOptional 0x-prefixed 32-byte salt. A random salt is used when omitted.
buyerYesChecksummed buyer address. This wallet would sign. The tool does not sign.
sellerYesChecksummed seller address, different from the buyer.
manifestYesAgreed deal text. It is hashed locally and is not stored by this tool.
amount_usdcYes
decision_windowYes
delivery_windowYes
acceptance_windowYes
arbitration_windowYes
fallback_seller_bpsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior5/5

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

The description goes well beyond the annotations by enumerating the side effects it explicitly avoids: it does not store the manifest, hold a key, sign, or broadcast, and it refuses to build while funding is paused or closed. This is exactly the kind of disclosure an agent needs for a tool that emits signing payloads, and it is consistent with the readOnly/non-destructive annotations.

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?

Four short sentences, front-loaded with the core action and output form, followed by the negative guarantees and the refusal condition. No filler and nothing that could be trimmed without losing information.

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 11-parameter, 10-required tool with no output schema, the behavioral picture is well covered but the input picture is not. The description never explains the window fields, mode semantics, or the fallback_bps value, leaving the agent to guess at core deal terms.

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

Parameters2/5

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

With 36% schema description coverage and 11 parameters, the description needs to compensate but does not. The five window parameters, amount_usdc, and fallback_seller_bps have no description in the schema and no explanation here, so an agent has no guidance on units, formats, or what a window value means.

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 specific verb and output: 'Build two unsigned transactions ... a USDC approve and proposeDeal. Returns calldata only.' An agent knows exactly what artifact it gets back and that no state is changed. It stops short of a 5 because it does not differentiate itself from siblings like quote_fee or get_deal_status, which an agent might also reach for when initiating a deal.

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?

'Refuses when funding is paused or closed' provides a precondition but not usage guidance. There is no statement of when to call this versus quote_fee (fee estimation) or get_deal_status (checking an existing deal), so the agent must infer that this is the entry point for starting a deal from the title alone.

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

Deploy Server

Other Tools