# Tuk Tuk: Agent-Direct Score D (46.2%)

Site: https://www.tuktuk.london/
Report: https://directindex.org/r/tuktuk.london
Scanned: 2026-10-15 (Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.)
Tuk Tuk is hard for agents to use.
AI assistants can't open Tuk Tuk's website, so they go by what other sites say about it.

## Direct links
- Book directly: https://www.tuktuk.london/reservations (on the business's own site)
- Menu: https://www.tuktuk.london/_files/ugd/fc8ab2_0d0cd1a321dc44fe9b1ce0adbf35adbe.pdf
- Phone: 02081910055
- Address: Golders Green Road 115 NW11 8HR London

## Nearby, also direct
Places near Tuk Tuk that take a booking or an order on their own website, with no marketplace in between.
- Pizaza Golders Green (50 m): https://directindex.org/r/pizaza.com
- Hot Cut (50 m): https://directindex.org/r/hotcut.co.uk
- Pukush  (60 m): https://directindex.org/r/pukush.com
- Soyo (70 m): https://directindex.org/r/soyo.co.uk
- Sushimania (70 m): https://directindex.org/r/sushimania.co.uk

## What to fix first
- **The site turns away every visitor that isn't a browser, AI agents included.** (+25 points) A plain fetch was refused (cloudflare_challenge). Only a real browser got the page. Every AI crawler and agent gets turned away the same way, so Reachable scores 0 and the rest is measured on the page as the browser rendered it. Ask the host to let the AI user agents through. Guide: https://directindex.org/guides/blocking-ai-crawlers-without-knowing
- **Structured data is incomplete.** (+4 points) Missing: telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **Menu or price list is a PDF.** (+3 points) Most agents skip PDFs or read them badly. Publish it as an HTML page and keep the PDF as a download. Guide: https://directindex.org/guides/menu-pdf-ai

## Fix kit: What to paste

Structured data (JSON-LD). Paste it as one block in the page's head, or in the builder's custom code box. Change anything that's wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Restaurant",
  "name": "Tuk Tuk",
  "url": "https://www.tuktuk.london/",
  "telephone": "02081910055",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Golders Green Road 115",
    "postalCode": "NW11 8HR",
    "addressLocality": "London"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 51.5735202,
    "longitude": -0.2005609
  },
  "servesCuisine": [
    "asian"
  ],
  "acceptsReservations": "https://www.tuktuk.london/reservations",
  "hasMenu": "https://www.tuktuk.london/_files/ugd/fc8ab2_0d0cd1a321dc44fe9b1ce0adbf35adbe.pdf",
  "potentialAction": [
    {
      "@type": "ReserveAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://www.tuktuk.london/reservations",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      },
      "result": {
        "@type": "Reservation",
        "name": "Reservation"
      }
    }
  ]
}
</script>
```

## Already right
- **robots.txt lets AI crawlers in.** There's no robots.txt, which means everything is allowed.
- **Structured data found (LocalBusiness).** address
- **Booking on your own site.** Agents can book without going through a marketplace.

## Since the scan of 2026-10-14 (F then)
- Fixed: The site couldn't be read at all
- New: The site turned away every visitor that wasn't a browser; Structured data was incomplete; Menu was a PDF

## Where it stands
5842 of 8985 in London. Top 65% of the sites scanned in this index.

| What the top 10% of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | yes |
| Publish the menu or price list as HTML | 87% | no |
| Let AI crawlers in (no block at the server or in robots.txt) | 94% | no |
| Structured data with address, phone and hours | 64% | no |
| Have an llms.txt | 37% | no |

Nearest places in the index: BRACHA - Street Food & Neshama (B, 38 m, https://directindex.org/r/bracha.london); Pita (F, 43 m, https://directindex.org/r/pita.london); Pizaza Golders Green (B, 46 m, https://directindex.org/r/pizaza.com); Sushi Haven (C, 50 m, https://directindex.org/r/sushihaven.co.uk); Hot Cut (B, 52 m, https://directindex.org/r/hotcut.co.uk); Pukush  (B, 59 m, https://directindex.org/r/pukush.com); Soyo (B, 65 m, https://directindex.org/r/soyo.co.uk); Sushimania (B, 69 m, https://directindex.org/r/sushimania.co.uk); Novellino (F, 75 m, https://directindex.org/r/novellinorestaurant.com); Met Su Yan (F, 79 m, https://directindex.org/r/metsuyan.co.uk).

## What assistants answer
The assistants haven't been asked about this business yet. They're asked about the top-ranked businesses in each city index, and about any business as soon as it's claimed. Claim this page to be included.

The assistants were asked 23 everyday questions about London and named 108 places. Tuk Tuk wasn't one of them. See who was named: https://directindex.org/city/london/recommended


Compared with its peers: Sites built with Wix 52% (28% A or B, 48660 sites); This site 46.2%.

See what an AI agent reads on this site: https://directindex.org/r/tuktuk.london/agent-view

## Businesses like Tuk Tuk in London

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in London | 8985 | 54% | 36% | 46.2% |
| Sites built with Wix in London | 692 | 70% | 54% | 46.2% |

The best of the sites built with Wix in London: Al-Fanar (A 100%, https://directindex.org/r/alfanarrestaurant.com); Bali Satay House (A 100%, https://directindex.org/r/balisatayhouse.co.uk); Deea Bangladeshi Cuisine (A 100%, https://directindex.org/r/deea.co.uk); Ember & Cork (A 100%, https://directindex.org/r/emberandcork.co.uk); Gold Mine (A 100%, https://directindex.org/r/goldminerestaurant.com).

With the three fixes above (The site turns away every visitor that isn't a browser, AI agents included; Structured data is incomplete; Menu or price list is a PDF), the score would be about 95.4%. That would be 187th of 8,985 in London, up from 5842nd.

## The direct record
What agents get for Tuk Tuk, as JSON: https://directindex.org/api/direct/tuktuk.london
- Book: https://www.tuktuk.london/reservations (own site; found by the scan of 2026-10-15, not yet tested)
- Order: none on record
- Menu: https://www.tuktuk.london/_files/ugd/fc8ab2_0d0cd1a321dc44fe9b1ce0adbf35adbe.pdf (pdf; from the scan)
- Hours: none on record
- Phone: 02081910055
- Stable links that count: https://directindex.org/go/tuktuk.london/book, https://directindex.org/go/tuktuk.london/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

Only a real browser got this page (a plain fetch got cloudflare_challenge); Readable and Actionable were measured on the rendered page.

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

## Agent readiness (Cloudflare)
Not measured for this scan.
- JSON-LD for the business: yes

Keep watching this business (https://directindex.org/r/tuktuk.london/plan): the assistants are asked again every month, and you see what changed. 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/tuktuk.london/deep. Ten questions phrased the way people ask them, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF. 5 EUR, paid once. 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=tuktuk.london&force=1