download_document_content
Downloads original document content (e.g., PDF) to a local folder without checking out the document. Provides read-only access for downstream processing of file bytes.
Instructions
Downloads a document's original content (e.g., the raw PDF file) from the content repository to a local folder WITHOUT checking the document out.
This is a read-only operation: it places NO reservation/lock on the document, so no checkin_document or cancel_document_checkout call is needed afterwards. Use this tool when the original file bytes are needed (e.g., for downstream image or PDF processing) rather than the extracted text.
:param identifier: The document id or path (required). This can be either the document's ID (GUID) or its path in the repository (e.g., "/Folder1/document.pdf"). :param download_folder_path: Path to the folder where the document content will be saved (required). The folder is created if it does not exist.
:returns: If successful, returns a dictionary containing: - document_id (str): The document's ID. - files (list): One entry per downloaded content element, each containing: - file_path (str): The full path of the downloaded file. - retrieval_name (str): The content element's original file name. - content_type (str): The MIME type of the content. - content_size (int): The size of the content in bytes. If unsuccessful, returns a ToolError with details about the failure.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| identifier | Yes | ||
| download_folder_path | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |