> For the complete documentation index, see [llms.txt](https://developer.esw.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.esw.com/agentic-commerce/esw-agentic-discovery/merchant-center-and-catalog-preparation.md).

# Merchant Center and Catalog Preparation

Prepare catalog data for agentic product discovery.

Provide a single CSV catalog per market so ESW can prepare products for agent-led discovery and checkout.

Include every required field for each product:

* `productId`
* `title`
* `description`
* `countryOfOriginIso`
* `availability`
* `price`
* `currencyIso`
* `link`
* `imageLink`

Also include conditional fields where applicable. For Apparel & Accessories, include `color, ageGroup & material`.

See the complete [product catalog specification](/agentic-commerce/esw-agentic-discovery/product-catalog-specification.md) for field formats and conditional requirements.

{% hint style="success" %}
**Pro Tip**

Would Microsoft Copilot, Google Gemini, or a Shopify shopping assistant know why your product is the best match? Think about what makes your products different to your competitors!
{% endhint %}

### Ingestion and enrichment

ESW enriches your catalog with AI-readable descriptions. These descriptions help AI agents understand your products and match them to shopper needs.

Clear descriptions explain a product's purpose and intended use. This helps Microsoft, Google, and Shopify assistants recommend relevant products with confidence.

### Enhanced data distribution

ESW sends your enriched catalog to the relevant merchant center, starting with Microsoft Merchant Center. Provide one product catalog per market so each audience receives the right language, price, availability, and enriched descriptions.

Tailor each catalog to preserve visibility in every market.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://developer.esw.com/agentic-commerce/esw-agentic-discovery/merchant-center-and-catalog-preparation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.