feat: browser_choose_file (#52)

Resolves https://github.com/microsoft/playwright-mcp/issues/31.

Prompt used for testing: 
```
upload test.txt to dropbox
```

This won't work for asynchronously opened filechoosers, but let's start
with the synchronous variant. I also tested with including the file
chooser open state in the snapshot, but that didn't give better results.

I also tested with OneDrive and WeTransfer, but somehow our ARIA
snapshots for those pages are missing some elements that are crucial to
locate the upload buttons.

README.md

@@ -203,6 +203,11 @@ The Playwright MCP provides a set of tools for browser automation. Here are all
     - `ref` (string): Exact target element reference from the page snapshot
     - `values` (array): Array of values to select in the dropdown.
 
+- **browser_choose_file**
+  - Description: Choose one or multiple files to upload
+  - Parameters:
+    - `paths` (array): The absolute paths to the files to upload. Can be a single file or multiple files.
+
 - **browser_press_key**
   - Description: Press a key on the keyboard
   - Parameters:
@@ -283,6 +288,11 @@ Vision Mode provides tools for visual-based interactions using screenshots. Here
   - Parameters:
     - `key` (string): Name of the key to press or a character to generate, such as `ArrowLeft` or `a`
 
+- **browser_choose_file**
+  - Description: Choose one or multiple files to upload
+  - Parameters:
+    - `paths` (array): The absolute paths to the files to upload. Can be a single file or multiple files.
+
 - **browser_save_as_pdf**
   - Description: Save page as PDF
   - Parameters: None