Skip to main content
Glama
Substack, B2B Churn & Lead MCP Server

Substack, B2B Churn & Lead MCP Server

by willowswt

mine_shopify_competitor_churn_reviews

Read-onlyIdempotent

Mine low-star Shopify App Store competitor reviews, score churn intent, extract pain signals and merchant contact data to identify switching leads.

Instructions

Mine angry 1-star and 2-star merchant reviews on any Shopify App Store competitor (appSlug like 'klaviyo-email-marketing', 'yotpo-social-reviews', 'gorgias-helpdesk'). Scores switching/churn intent (0-100), extracts pain signals, merchant name, country, app tenure, and probes merchant domain/emails.

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": {
      "appSlug": "<appSlug>"
    },
    "name": "mine_shopify_competitor_churn_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
appSlugYesShopify App Store slug or URL (e.g. 'klaviyo-email-marketing').
maxReviewsNoMaximum low-star reviews to return (1-25, default 10).
resolveMerchantDomainsNoProbe live Shopify storefront domain & contact email (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds real behavior beyond them: the tool probes live merchant domains and contact emails (the external side effect behind openWorldHint), and it computes a 0-100 churn-intent score plus pain-signal extraction. It stops short of stating cost, rate limits, or what happens when a merchant has no public domain/email.

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?

A single dense sentence with the resource scope front-loaded before the field list, and no filler. The parenthetical of example slugs is long but directly useful for slug formatting; the output-field enumeration is tighter than it could have been.

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 return-value burden and does so by enumerating churn score, pain signals, merchant name, country, app tenure, and probed domain/emails. Combined with 100% schema coverage on inputs, an agent has enough to call it correctly, though the probing side effect and failure modes are only lightly covered.

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 description coverage is 100%, including slug format example, the 1-25 range on maxReviews, and the semantics of resolveMerchantDomains, so the baseline is 3. The description only echoes the appSlug example and the domain/email probing already documented in the schema, adding no new parameter meaning.

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 (mine) and a tightly scoped resource (1-star and 2-star merchant reviews on any Shopify App Store competitor), and supplies three concrete appSlug examples so the target data is unmistakable. This is clearly distinct from the email-extraction, HN/ProductHunt, and Substack siblings without needing to name them.

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 only implied: an agent can infer this is for competitive churn analysis on a named Shopify app. There is no explicit when-to-use, no when-not, no prerequisite or quota context, and no routing to an alternative tool for other review types or non-Shopify platforms.

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