pdf_chunk
Split PDFs into structure-aware semantic chunks with dynamic overlap for AI agents and LLM context windows, outputting JSON for downstream processing.
Instructions
Structure-aware semantic chunking with dynamic overlap for AI agents and LLM context windows. [Input: PDF (.pdf) | Output: 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": {
"input": "<input>"
},
"name": "pdf_chunk"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Path to input PDF file | |
| output | No | Optional destination path for JSON output | |
| target_tokens | No | Target tokens per chunk (default: 500, range: 50-4000) | |
| overlap_tokens | No | Overlap tokens between chunks (default: 50, range: 0-500) | |
| break_on_headings | No | Trigger hard boundary split on # / ## headings (default: true) | |
| strip_boilerplate | No | Strip repetitive headers/footers across consecutive pages (default: true) |