This tool is used to search and retrieve information from specific websites by connecting to a data store.

When you first create the tool, you provide:

- **Name**: A descriptive name that helps the AI understand the tool's job. Names should start with a verb (for example, search_knowledge_base).

- **Description**: (Optional) An explanation of what the tool does and when the AI should use it.

- **Location**: The region where the data store is hosted (for example, global).

- **Mock tool response**: An optional configuration used to simulate the tool's output for testing purposes before the data is fully indexed.

- **Sites to include** : A list of URLs to index. Use `yoursite.com/*` to index an entire site or `yoursite.com/page/*` to index a specific page.

- **Sites to exclude**: Specific URLs or patterns that the tool should ignore.

## Limitations:

- You must [verify your domain](https://docs.cloud.google.com/generative-ai-app-builder/docs/domain-verification.md.txt) when using website content as a source.
- Files from public URLs must have been crawled by the Google Search indexer, so that they exist in the search index. You can check this with the [Google Search Console](https://search.google.com/search-console).
- A maximum of 200,000 pages are indexed. If the data store contains more pages, indexing will fail at that point. Any content already indexed will remain.

See also [Create a data store using website content](https://docs.cloud.google.com/generative-ai-app-builder/docs/create-data-store-es.md.txt#website).