extract_structured_data
Convert raw text, email bodies, receipts, logs, or HTML snippets already in memory into strict typed JSON conforming to target_schema. Use when you already have the source text and need deterministic schema enforcement without burning local reasoning tokens. Strictly capped at 6,000 bytes.
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": {
"raw_text": "<raw_text>"
},
"name": "extract_structured_data"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| raw_text | Yes | Unstructured text, HTML fragment, or document snippet to normalize (max 6,000 bytes). | |
| target_schema | No | Declarative key-type map defining the exact JSON structure to return. |