Skip to main content
Glama
stablevoy-mcp

stablevoy-mcp

Official

Read where buyers stop on the payment page

get_checkout_funnel
Read-onlyIdempotent

Shows where buyers stop during payment for invoices created in a chosen period by counting invoice stage progression, helping identify payment drop-off.

Instructions

Gets where buyers stop on the payment page for the invoices created in a period. Needs a store key (npx stablevoy-mcp login). It counts invoices, not visits: how many were opened (on the hosted page or in the widget), had the network or token changed, had the details copied, started a wallet, were refused or failed in the wallet, had a transaction sent, saw a payment (detected) and were paid. Nothing about the buyer is kept. A buyer who pays from another device skips page steps, so read it as a guide. Pass either period or both createdFrom and createdTo as UTC days, at most 92 days per call. A period together with dates, or only one date, is refused. Without store and with several stores you get one funnel per store plus a total. Use get_checkout_trail for the steps of one invoice and summarize_payments for the money. The API allows 30 calls a minute per store. A failure comes back as an error with its code and what to do, for example rate_limited with the seconds to wait.

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": "get_checkout_funnel"
  }
}

Input Schema

NameRequiredDescriptionDefault
storeNoStore id or exact store name from list_stores. Needed only when several stores are connected.
periodNoA ready-made range of UTC days ending today. Leave out when giving dates.
createdToNoLast UTC day, YYYY-MM-DD, included.
createdFromNoFirst UTC day, YYYY-MM-DD, with createdTo.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.9.0

TDQS

A4.7/5.0
Behavior4/5

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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses an auth prerequisite (store key via npx login), a privacy property ('Nothing about the buyer is kept'), a data-quality caveat (cross-device payers skip page steps, so read as a guide), a rate limit (30 calls/minute per store), and the error contract (code plus remediation, e.g. rate_limited with seconds to wait). That is substantial disclosure; only the exact response shape/pagination is left implicit, which is minor given there is no output schema.

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?

Front-loaded with purpose and scope, and every sentence carries information (auth, counting definition, caveat, argument rules, alternatives, rate limit, errors). It is dense and the long verb enumeration of funnel steps is heavy, but it is not padded with 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?

With no output schema, the description carries the burden of describing the return and does so: per-step invoice counts, per-store funnels plus a total when store is omitted, and an error envelope. Combined with the argument rules and rate limit, an agent has everything needed to call this correctly and interpret results.

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

Parameters5/5

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

Schema coverage is already 100%, but the description adds meaning the schema cannot express: period and createdFrom/createdTo are mutually exclusive, only one date is rejected, and the window is capped at 92 UTC days per call. It also clarifies that store is optional and only matters when several stores are connected.

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 verb ('Gets') and resource ('where buyers stop on the payment page for the invoices created in a period') and then enumerates the exact funnel steps counted (opened, token/network changed, details copied, wallet started, refused/failed, transaction sent, payment detected, paid). It also explicitly names the siblings it is not (get_checkout_trail for one invoice, summarize_payments for money), so the agent can separate it from neighbors without reading the schemas.

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

Usage Guidelines5/5

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

Gives explicit selection rules and exclusions: use get_checkout_trail for a single invoice's steps and summarize_payments for money figures. It also states the argument combination rules (period XOR createdFrom+createdTo, at most 92 days, one date alone is refused) and the multi-store behavior (no store with several connected returns one funnel per store plus a total).

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