# Han Shi Fang: Agent-Direct Score B (76.9%)

Site: https://hanshifang.fr/
Report: https://directindex.org/r/hanshifang.fr
Scanned: 2026-10-21 (Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.)
Han Shi Fang is mostly ready for agents.
An AI assistant can open Han Shi Fang's website. It can read what Han Shi Fang offers. To book or order, it is sent to Uber Eats, a marketplace.

## Direct links
- Menu: https://hanshifang.fr/fr/#menu
- Phone: +33 1 53 72 90 16
- Hours, from OpenStreetMap · Overture Maps: Mon–Sun 18:00–22:30

## Nearby, also direct
Places near Han Shi Fang that take a booking or an order on their own website, with no marketplace in between.
- Yi Bowl Noodle (40 m): https://directindex.org/r/yibowlnoodle.com
- Auciel (60 m): https://directindex.org/r/aucielparis.com
- Wukong The Grand Master (450 m): https://directindex.org/r/wukongrestaurant.com
- Shodai Matcha (470 m): https://directindex.org/r/shodaiparis.fr
- Lucky (550 m): https://directindex.org/r/luckyparis.fr

## What to fix first
- **Ordering only through ubereats.** (+12 points) Every transaction an agent makes goes through the marketplace, which takes its commission. Add a direct way on your own site. Even a simple form will do. Guide: https://directindex.org/guides/online-ordering-without-delivery-apps
- **Structured data is incomplete.** (+3 points) Missing: opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **No llms.txt.** (no points, but worth doing) Optional for now and cheap to add. It's a short text file that describes the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## What the site tells visitors (Measured, not scored)
- **No English version declared.** Visitors from abroad, and assistants answering in English, read the page as it is. In Paris, 34% of comparable sites declare one.

## 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": "Han Shi Fang",
  "url": "https://hanshifang.fr/",
  "telephone": "+33 1 53 72 90 16",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 48.8686409,
    "longitude": 2.35998
  },
  "openingHours": "We-Su 12:00-14:30; Mo-Su 18:00-22:30",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Wednesday",
        "Thursday",
        "Friday",
        "Saturday",
        "Sunday"
      ],
      "opens": "12:00",
      "closes": "14:30"
    },
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Monday",
        "Tuesday",
        "Wednesday",
        "Thursday",
        "Friday",
        "Saturday",
        "Sunday"
      ],
      "opens": "18:00",
      "closes": "22:30"
    }
  ],
  "servesCuisine": [
    "chinese"
  ],
  "hasMenu": "https://hanshifang.fr/fr/#menu"
}
</script>
```

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

```
# Han Shi Fang

> restaurant (chinese) in Paris. Phone +33 1 53 72 90 16.

## Book or order directly

- Menu: https://hanshifang.fr/fr/#menu

## Opening hours

We-Su 12:00-14:30; Mo-Su 18:00-22:30

## About

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

## Already right
- **robots.txt lets AI crawlers in.** There's no robots.txt, which means everything is allowed.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all got a normal response.
- **Structured data found (Restaurant).** address, phone
- **Menu or price list is an HTML page.** Agents can read the items and prices.
- **Uber Eats works with agents through its partners.** Uber's US terms of use (12 October 2026) bar scripts that burden the services and any use to build software or train AI; its Claude and ChatGPT integrations only browse menus, with checkout in the Uber Eats app. Terms read on 2026-10-15: https://www.uber.com/legal/en/document/?name=general-terms-of-use&country=united-states&lang=en. An assistant that isn't a partner may not be able to finish there. A direct path on your own domain works for all of them.

## Where it stands
1309 of 5992 in Paris. Top 22% 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% | no |
| Publish the menu or price list as HTML | 99% | yes |
| Let AI crawlers in (no block at the server or in robots.txt) | 99% | yes |
| Structured data with address, phone and hours | 84% | no |
| Have an llms.txt | 61% | no |

Nearest places with a similar menu: Guimi House (F, 13 m, https://directindex.org/r/guimi.fr); Yi Bowl Noodle (A, 41 m, https://directindex.org/r/yibowlnoodle.com); Auciel (A, 57 m, https://directindex.org/r/aucielparis.com); Le Jardin (D, 225 m, https://directindex.org/r/github.io); Wukong The Grand Master (A, 447 m, https://directindex.org/r/wukongrestaurant.com); Shodai Matcha (B, 471 m, https://directindex.org/r/shodaiparis.fr); Coin de Paradis (F, 539 m, https://directindex.org/r/newsavour.com); Lucky (D, 554 m, https://directindex.org/r/luckyparis.fr); Happy Nouilles (C, 582 m, https://directindex.org/r/happynouilles.com); Yuxiangting (D, 606 m, https://directindex.org/r/yuxiangting.fr).

## 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 30 everyday questions about Paris and named 198 places. Han Shi Fang wasn't one of them. See who was named: https://directindex.org/city/paris/recommended


Compared with its peers: Sites using Uber Eats 61% (32% A or B, 2434 sites); This site 76.9%.

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

## Businesses like Han Shi Fang in Paris

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Paris | 5992 | 57% | 39% | 76.9% |
| Sites using Uber Eats in Paris | 78 | 68% | 50% | 76.9% |

The best of the sites using Uber Eats in Paris: Naruto Ramen (A 100%, https://directindex.org/r/narutoramen.fr); Mohae (A 94.9%, https://directindex.org/r/mohae.fr); Bacioni (A 92.3%, https://directindex.org/r/bacioni-restaurant.com); Jules Jo (A 92.3%, https://directindex.org/r/julesjo.com); Mama Kossa (A 92.3%, https://directindex.org/r/mamakossa.fr).

With the two fixes above (Ordering only through ubereats; Structured data is incomplete), the score would be about 100%, which would be first of 5,992 in Paris.

## The direct record
What agents get for Han Shi Fang, as JSON: https://directindex.org/api/direct/hanshifang.fr
- Book: none on record
- Order: none on record
- Menu: https://hanshifang.fr/fr/#menu (html_page; from the scan)
- Hours: We-Su 12:00-14:30; Mo-Su 18:00-22:30 (closed now) (from OpenStreetMap)
- Phone: +33 1 53 72 90 16
- Stable links that count: https://directindex.org/go/hanshifang.fr/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
- Vendor terms for agents, Uber Eats: Through partners. Uber's US terms of use (12 October 2026) bar scripts that burden the services and any use to build software or train AI; its Claude and ChatGPT integrations only browse menus, with checkout in the Uber Eats app. Read 2026-10-15: https://www.uber.com/legal/en/document/?name=general-terms-of-use&country=united-states&lang=en

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 22 | 25 |
| Actionable | 3 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 0 of 5, Not Ready. Cloudflare's report: https://isitagentready.com/hanshifang.fr
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: no (how: https://isitagentready.com/.well-known/agent-skills/sitemap/SKILL.md)
- AI bot rules in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/ai-rules/SKILL.md)
- 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/hanshifang.fr/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/hanshifang.fr/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=hanshifang.fr&force=1
