get_chunk
Fetch a document chunk by its ID to view full content. Optionally include neighboring chunks and document metadata for context, so you can expand search results lazily.
Instructions
Retrieve full content of a specific chunk by ID. Use this after search_docs to lazily expand only the chunks you need. Optionally include neighboring chunks (prev/next) and document metadata.
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": {
"id": "<id>"
},
"name": "get_chunk"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Chunk ID from search_docs result. | |
| token_budget | No | Max tokens for content. Content truncated if over budget. | |
| include_neighbors | No | Include prev/next chunk summaries for context. | |
| include_document_meta | No | Include document metadata (title, fetched_at, URL). |