# Structured data

**Canonical URL:** https://teas.co.uk/ai/structured-data/
**Source:** teas.co.uk, UK tea specialist, Tunbridge Wells, Kent

## Shop teas.co.uk from an AI assistant (MCP)

teas.co.uk sells tea, herbal and fruit infusions, hot chocolate and Border biscuits.
MCP server: https://teas.co.uk/mcp (Streamable HTTP), listed in the official MCP Registry as teas.co.uk
Backup address (same server, same tools; use it if /mcp is blocked): https://teas.co.uk/wp-json/teas/v1/shop-mcp
Server card: https://teas.co.uk/.well-known/mcp/server-card.json
Tools: find_products, get_product, compare_products, find_recipes, delivery_and_returns, quote_cart, get_promotions, report_problem, find_substitutes, start_subscription, join_teas, ask_lee, tea_page, search_tea_wiki, read_wiki_article, brand_page, teas_home, browse_shop, browse_recipes, recipe_page, teas_news, read_news, under_the_hood, teas_socials, teas.
Basket: add_to_basket, view_basket, update_basket, checkout_link, checkout_session, basket.
With sign in: get_return_status, get_invoice, get_profile, my_orders, track_order, reorder, my_subscriptions, change_subscription, rewards_balance, start_return, my_account.
No sign in is needed to search, compare, build a basket or get a checkout link. The person always pays on teas.co.uk.
Cards: in assistants that draw MCP Apps cards, products, comparisons, the basket, checkout, orders, repeat deliveries (pause, resume, cancel), reward points and returns appear as cards.
Every assistant except ChatGPT, until OpenAI approves the next version: quote_cart, get_promotions, get_return_status, get_invoice, report_problem, find_substitutes, start_subscription, join_teas, ask_lee, tea_page, search_tea_wiki, read_wiki_article, brand_page, teas_home, browse_shop, browse_recipes, recipe_page, teas_news, read_news, under_the_hood, teas_socials, teas, basket, my_account.
Set up guides: https://teas.co.uk/ai/

## Summary

Structured data is information arranged in named fields. A person can understand “a box of 50 decaf green tea bags”. Software benefits from separate…

## Description

Structured data is information arranged in named fields. A person can understand “a box of 50 decaf green tea bags”. Software benefits from separate labels for the product name, quantity, tea type and caffeine status.
Labels are how software knows that “50” is the number of tea bags and not the price. The labels make the information easier to compare. They do not make it true by themselves.
Labels turn tea facts into something any system can read, through schema.org and the small records beside every picture. They make facts easier to compare. They cannot prove them.
A tea example
For a product, the shop can record its name, identifier, pack size, price, currency and availability. A customer reads those facts on a page. Another system can receive values with explicit labels rather than guessing which number in a paragraph is the price.
Price per cup is a good example of a field a tea shop needs that a general vocabulary does not hand it ready-made. It is one of the most useful labels in the shop, because it is the fairest way to compare a 40-bag box with a 240-bag box. teas.co.uk keeps it in its own records alongside the standard product facts.
What are schema.org and JSON-LD?
schema.org is a shared vocabulary for describing web content. JSON-LD is a way of writing structured data that can sit in a page. Both help software understand which value is the name, which is the price and which is the brand. They do not certify that the values are correct.
Is it different from an API?
Yes. Structured data describes how information is organised. An API describes how software can request information or use a service. An API response can contain structured data, and a normal web page can contain it too.
What should a shopper expect?
Clearer comparisons, the right pack attached to the right price, and an explicit answer when an attribute is unknown. A blank ingredient or allergy field should never become a confident “free from” claim.
Structured data does not guarantee a search appearance or an assistant recommendation. At teas.co.uk it supports a more basic aim: one authoritative source for the facts a person and a machine share.
Why a tea shop labels its facts
People are starting to ask AI assistants which tea to buy instead of typing two words into a search box. An assistant sent to answer “a decaf Earl Grey that is good value” goes out, reads shops, guides and data, checks prices and pack sizes and whether the tea really is decaf, then reports back. That assistant cannot squint at a photograph of the back of a box to work out the caffeine. It needs the facts laid out, labelled and sourced.
I built teas.co.uk so that an independent tea shop could be that source. An assistant that guesses will sometimes get it wrong, so given a choice between a tidy source and a messy one it will take the tidy one. Labelled facts are how a small shop becomes the tidy one.
A paragraph of product copy is written for people. A labelled record is written for both: the shopper reads the page, and software reads the same facts with their names attached.
Files that sit beside every page and picture
Labels behind product pages are only the start. The shop also publishes sidecar files next to images and discovery files that tell software where the facts live and how to ask for them.

---

_Content available under teas.co.uk citation contract. AI training: yes. Search: yes. Answer-input: yes._
