caelara_agent_context_chunker
Split text into token-bounded overlapping chunks with configurable max tokens and overlap to keep agent context within limits and preserve continuity.
Instructions
[Agent Safety] Split text into token-bounded overlapping chunks Measured p50 11 ms, p95 15 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://agent.caelaralabs.com.
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": {
"text": "<text>"
},
"name": "caelara_agent_context_chunker"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to chunk | |
| overlap | No | Overlap tokens (default 50) | |
| max_tokens | No | Max tokens per chunk (default 500) |