get_index
Retrieve a document's outline, table and figure captions with page positions, plus pages lacking text or with low-resolution images, to locate content in large datasheets.
Instructions
The index of a document: the outline (bookmarks or numbered headings) with pages, and the table and figure captions with their page and position. A large document gives only the top outline levels: get_outline gives the entries under a section. Also the pages with no text layer or with images of a low resolution. Start here to find where the content is.
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>"
},
"name": "get_index"
}
}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. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |