Skip to main content
Glama
Sign In

Fudge for Shopify

by ai.fudge
OverviewDiscussionsAdmin

Check catalogue data

check_catalog_data
Read-onlyIdempotent

Check catalogue data coverage across published products, collections, pages and articles: taxonomy, SEO fields, product type, vendor, description, images, alt text and optionally GTIN and MPN. Without type, totals and per-field coverage; with type, the items missing fields, a page at a time. The first call scans the live catalogue and can return status "scanning". Results are kept for an hour.

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": "check_catalog_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoList this type’s offenders instead of the summary.
limitNo
storeNoThe connected store to use. Omit when only one is connected.
offsetNo
missingNoWith type: only items missing this field, named as in the summary, e.g. "Meta description".
refreshNoRescan instead of reusing this hour’s result. Only after the merchant changed catalogue data.
includeProductIdentifiersNoAlso check GTIN/barcode and MPN on products. A separate, slower scan.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world, but the description adds information structured fields cannot convey: the first call scans live and may return status "scanning", results are cached for an hour, and `includeProductIdentifiers` triggers a separate slower scan. Those latency, async-state and caching traits are exactly what an agent needs to sequence calls without retry loops.

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, front-loaded with the scope, then the two-mode behavior, then the operational caveats about scanning and the one-hour cache. No filler and no repetition of schema or annotation content.

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 7-parameter read tool with annotations but no output schema, it covers the mode switch, pagination ('a page at a time'), caching, and the slower identifier scan. What is missing is any hint of the result shape beyond the field names checked, which matters since there is no output schema to fall back on.

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

Parameters4/5

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

Beyond the 71% schema coverage it clarifies the summary-versus-offenders switch driven by `type`, that `missing` must be named as in the summary (e.g. "Meta description"), that `refresh` bypasses the hourly cache, and that identifier checking is a slower separate scan. Only `limit` and `offset` get no added meaning, though their schema defaults make them self-evident.

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?

States a specific verb and resource ('Check catalogue data coverage') and scopes it precisely to published products, collections, pages and articles, enumerating the fields audited. An agent knows exactly what the tool inspects; the only gap is that it never names or contrasts the closest sibling, run_catalog_data_audit.

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

Usage Guidelines4/5

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

Gives clear conditional usage: without `type` you get totals and per-field coverage, with `type` you get the offending items paged one page at a time. It also constrains `refresh` to 'Only after the merchant changed catalogue data' and explains when to omit `store`. No explicit exclusion relative to sibling tools, which keeps it from a 5.

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

All Fudge for Shopify 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