# Tea Island: Agent-Direct Score C (58.2%)

Site: https://teaisland.co.uk/
Report: https://directindex.org/r/teaisland.co.uk
Scanned: 2026-10-15 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Tea Island is partly visible to agents.
Some AI assistants are turned away by the website of Tea Island. It can read what Tea Island offers. It finds no link to book or order online, only a phone number.

## Direct links
- Menu: https://teaisland.co.uk/menu
- Phone: 07846-234673

## What to fix first
- **No booking or ordering link on the website.** (+13 points) Only a phone number or WhatsApp, which agents cannot use yet. If you take bookings or orders through a platform, link to it from the site so an agent can find it. Add a booking or ordering page. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **robots.txt blocks GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot.** (+6.2 points) These are the crawlers behind ChatGPT, Claude, Perplexity and Google's AI features. Remove the Disallow lines for them, or add explicit Allow rules. Guide: https://directindex.org/guides/robots-txt-for-ai-agents
- **Structured data is incomplete.** (+5 points) Missing: address, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **No llms.txt.** (no points, still worth doing) Optional today, cheap to add: a short text file describing the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## Fix kit: What to paste

Structured data (JSON-LD). One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "CafeOrCoffeeShop",
  "name": "Tea Island",
  "url": "https://teaisland.co.uk/",
  "telephone": "07846-234673",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "High Street 168",
    "postalCode": "RM12 6AF",
    "addressLocality": "Hornchurch"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 51.5614943,
    "longitude": 0.2211392
  },
  "hasMenu": "https://teaisland.co.uk/menu"
}
</script>
```

robots.txt. Add these lines to /robots.txt and delete any Disallow rule that names these crawlers.

```
# Let AI assistants read the site: they send people to you; a marketplace keeps them.
# Remove any Disallow lines for these names elsewhere in this file.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /
```

llms.txt. Save as /llms.txt at the root of the site.

```
# Tea Island

> cafe or coffee shop in High Street 168 RM12 6AF Hornchurch, London cafes and bars. Phone 07846-234673.

## Book or order directly

- Menu: https://teaisland.co.uk/menu

## About

- Website: https://teaisland.co.uk/
- This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
```

## Already right
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Structured data present (LocalBusiness).** phone
- **Menu or price list is an HTML page.** Agents can read items and prices directly.

## Since the scan of 2026-10-14 (C then)
- Fixed: nothing
- New: nothing

## Where it stands
1208 of 2270 in London cafes and bars. Top 53% of the sites scanned in this index.

| What the top tenth of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | no |
| Publish the menu or price list as HTML | 96% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 98% | no |
| Structured data with address, phone and hours | 68% | no |
| Have an llms.txt | 11% | no |

Nearest places in the index: Hop Inn Micropub (D, 699 m, https://directindex.org/r/hopinnhornchurch.com); Pop In Sandwich bar (D, 2470 m, https://directindex.org/r/popinsandwichbaressex.co.uk); Cafe 108 (B, 2491 m, https://directindex.org/r/cafe108.co.uk); Hope Cafe (F, 3314 m, https://directindex.org/r/hopecafe.live).

## What assistants answer
Not asked yet. Assistants are asked about the top-ranked businesses in each city index, and about every claimed business the moment it is claimed; claim this page to be included.

Score over 2 scans since 2026-10-14: 2026-10-14 58%, 2026-10-15 58%.

See what an AI agent reads on this site: https://directindex.org/r/teaisland.co.uk/agent-view

## Businesses like Tea Island in London cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in London cafes and bars | 2270 | 52% | 37% | 58.2% |

The best of the businesses of the same kind in London cafes and bars: And Then (A 100%, https://directindex.org/r/andthentooting.com); Bar Américain (A 100%, https://directindex.org/r/brasseriezedel.com); Bar Soho (A 100%, https://directindex.org/r/barsoho.co.uk); Conuco (A 100%, https://directindex.org/r/conuco.co.uk); George's Cafe Brockley (A 100%, https://directindex.org/r/georgescafebrockley.uk).

With the three fixes above (No booking or ordering link on the website; robots.txt blocks GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot; Structured data is incomplete) the score would be about 95.4%: 16th of 2,270 in London cafes and bars, up from 1208th.

## The direct record
What agents get for Tea Island, as JSON: https://directindex.org/api/direct/teaisland.co.uk
- Book: none on record
- Order: none on record
- Menu: https://teaisland.co.uk/menu (html_page; from the scan)
- Hours: none on record
- Phone: 07846-234673
- Stable links that count: https://directindex.org/go/teaisland.co.uk/menu

## Can an agent transact?
Measured, not scored (the score stays at spec v1.0).
- UCP profile (/.well-known/ucp, Google and Shopify's Universal Commerce Protocol): no
- ACP discovery document (/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol): no
- MCP server card (/.well-known/mcp/server-card.json): no
- Ordering vendor that takes agent orders (Square, Toast, or a vendor whose terms allow agents): no

Found one hop past the home page: menu page /menu: almost no text without JavaScript.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 18.8 | 25 |
| Readable | 17 | 25 |
| Actionable | 2 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 1 of 5, Basic Web Presence. Cloudflare's report: https://isitagentready.com/teaisland.co.uk
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: yes
- AI bot rules in robots.txt: yes
- Content Signals in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/content-signals/SKILL.md)
- Markdown on Accept: text/markdown: no (how: https://isitagentready.com/.well-known/agent-skills/markdown-negotiation/SKILL.md)
- llms.txt: no (how: https://isitagentready.com/.well-known/agent-skills/llms-txt/SKILL.md)
- API catalog (RFC 9727): no (how: https://isitagentready.com/.well-known/agent-skills/api-catalog/SKILL.md)
- MCP server card: no (how: https://isitagentready.com/.well-known/agent-skills/mcp-server-card/SKILL.md)
- A2A agent card: no (how: https://isitagentready.com/.well-known/agent-skills/a2a-agent-card/SKILL.md)
- Agent Skills index: no (how: https://isitagentready.com/.well-known/agent-skills/agent-skills/SKILL.md)
- OAuth or OIDC discovery: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-discovery/SKILL.md)
- OAuth protected resource metadata: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-protected-resource/SKILL.md)
- auth.md: no (how: https://isitagentready.com/.well-known/agent-skills/auth-md/SKILL.md)
- Web Bot Auth key directory: no (how: https://isitagentready.com/.well-known/agent-skills/web-bot-auth/SKILL.md)
- ARD capability manifest: no (how: https://isitagentready.com/.well-known/agent-skills/ard/SKILL.md)
- DNS-AID records: no (how: https://isitagentready.com/.well-known/agent-skills/dns-aid/SKILL.md)
- WebMCP tools on the page: no (how: https://isitagentready.com/.well-known/agent-skills/webmcp/SKILL.md)
- JSON-LD for the business: yes

Keep watching this business (https://directindex.org/r/teaisland.co.uk/plan): the assistants asked again every month, with what changed; 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/teaisland.co.uk/deep. Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 5 EUR, one-off. Reading and scanning stay free; these few euros pay for the questions sent to the assistants and for the servers.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=teaisland.co.uk&force=1