read_pdf
Extract text from PDF files page by page to read, summarize, or answer questions from document contents. Supports up to 200 pages per call; specify max_pages for larger documents.
Instructions
Extract text from a PDF file, returned page by page. Use this when a user shares or mentions a PDF and wants you to read, summarise, or answer questions from its contents. Supports up to 200 pages per call (default 50); pass max_pages for larger documents. Encrypted/password-protected PDFs are not supported. Requires allow_file_read in ~/.syscontrol/config.json.
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": {
"path": "<path>"
},
"name": "read_pdf"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute or home-relative path to the .pdf file. | |
| max_pages | No | Maximum number of pages to read (1-200, default 50). |