get_element_text
Retrieve the full text, type, page, and region of datasheet elements such as headings and paragraphs. Use it to read text-layer content; get table, figure, and formula values from page images.
Instructions
The full text of elements from the text layer, with their type, page and region. Use it for headings and paragraphs. Read table values, figures and formulas from get_page_image: the text layer can lose their structure. The text of a table or figure is only its caption. For a table, figure or formula, the result also gives the call of get_page_image for its image (with the caption label of a table, the call that gives each page of a table that continues on the next pages).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"document": "<document>",
"element_ids": "<element_ids>"
},
"name": "get_element_text"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| document | Yes | The document: its reference from list_documents, project_status or add_document (the first 12 characters of its SHA-256). A longer SHA-256 prefix or the numeric document ID also works. | |
| element_ids | Yes | Element IDs from get_page_map or list_items, for example ["p7.T1", "p7.P3"]. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |