Skip to main content
Glama
shopify-partners-mcp

shopify-partners-mcp

by amitray007

retention_cohorts

Read-only

Groups shops by install month and reports the percent still installed and paying in each later month, so you can measure app retention over time.

Instructions

Shops grouped by the month they first installed. For each cohort: the percent still installed and the percent paying at the end of each later month. Computed from the app's full event history, which the server downloads once and caches for 15 minutes.

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": "retention_cohorts"
  }
}

Input Schema

NameRequiredDescriptionDefault
appIdNoApp ID: the number or a gid:// ID. Optional when SHOPIFY_PARTNER_APP_IDS names exactly one app
monthsNoHow many calendar months, ending with the current one

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already grant readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: the result is computed from the app's full event history, downloaded once by the server and cached for 15 minutes — telling the agent to expect potential first-call latency and up-to-15-minute staleness. It stops short of noting failure modes when history is incomplete.

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?

Three sentences, no filler, and the payoff statement — what each cohort row contains — is front-loaded ahead of the computational/caching note. Every sentence carries distinct information an agent would otherwise have to discover by calling the tool.

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?

With no output schema, the description carries the burden of describing return values, and it does: cohorts keyed by first-install month, each with percent-installed and percent-paying per later month. The caching note covers freshness. The only gap is nothing about output ordering, truncation at 60 months, or what the percentages are relative to (cohort size vs. prior month).

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% and both parameters (appId, months with default 12, range 1-60) are fully documented in the schema itself. The description's mention of 'the end of each later month' loosely implies the months window but adds no new constraint, format, or edge-case detail, so it sits at the baseline for a well-documented schema.

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 output shape: shops grouped by install month, with per-cohort percentages still installed and still paying in each later month. That is far more specific than a restatement of the name, but it never contrasts itself with nearby tools like churn_report, install_summary, or customer_ltv, so an agent must infer the boundary.

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 rather than stated: the metric list signals this is the tool for cohort retention/paid-retention curves, which implicitly excludes single-period counts or revenue breakdowns. There is no explicit when-to-use, when-not-to-use, or named alternative, so an agent choosing between this and churn_report or install_summary gets no routing help.

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