eg

product schema inspector.

paste a pdp url → see which product schema fields are missing

> worked example

A Shopify SEO lead pastes https://www.nike.com/t/pegasus-41-mens-road-running-shoes-vjWvr3/FD2722-101 into the inspector. The tool finds a valid Product block but flags three LLM-critical fields: offers.priceCurrency is missing, offers.availability is absent, and description is under 50 characters. Two recommended fields, gtin13 and aggregateRating, are also missing, meaning LLMs have almost no structured context to quote or compare this product accurately.

takeaway, A product page can rank well in traditional search but still be invisible to AI shopping assistants if its structured data is sparse.

> when operators reach for this

  • Shopify SEO leads auditing new product launches to confirm all schema fields are present before the PDP goes live.
  • Ecommerce data leads comparing schema coverage across a catalogue to prioritise which SKUs need schema enrichment first.
  • Headless commerce developers verifying that a new storefront renders JSON-LD that passes LLM-critical field checks.
  • Brand CMOs preparing for AI search, using the inspector to confirm product data is rich enough to appear in ChatGPT and Perplexity shopping answers.
  • Agencies running technical audits for clients, using the tool to export a list of missing recommended fields across a client's top-revenue PDPs.

> the calculation

  • llm-critical fieldsname, description, image, offers.price, offers.priceCurrency, offers.availabilityMissing any of these prevents LLMs from reliably describing or pricing the product.
  • recommended fieldsbrand, sku, gtin13 / gtin12 / gtin14 / mpn, aggregateRating.ratingValue, aggregateRating.reviewCountPresent = significantly higher chance of accurate AI citation and comparison.

> related calculators, ai & llm visibility