Chopper
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHOPPER_SNAP | No | sentence (default), word or none | sentence |
| CHOPPER_DEVICE | No | auto, cpu or cuda | auto |
| CHOPPER_VARIANT | No | base (default), small, base-pl or small-pl | base |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Chopper cuts exact quotes that answer a question out of long retrieved text (2-5% of it is typically kept). Call it BEFORE reading many search results, documents or files in full: pass the user's question and the raw text, then read the returned quotes instead of the whole text. Quotes are verbatim, with their source and character offsets. decision == 'SEARCH' means the text most likely does not contain the answer: search again or retrieve other documents rather than answering from it. The same call ranks the passages by relevance (ranking), so no separate reranker is needed; use rank_passages when whole passages, not quotes, are wanted.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chop_passagesA | Cut the exact quotes that answer |
| rank_passagesB | Rank |
| chop_filesA | Read local text files (notes, docs, logs, code, exported pages), split them into ~1,000-character passages and
cut out the exact quotes that answer |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
rank_passages is clearly distinct, and chop_passages vs chop_files differ by input source. However, the two chop tools share the same core extraction behavior and return shape, so an agent could briefly hesitate between them when file-derived snippets are involved.
All names use consistent snake_case verb_noun form: chop_passages, rank_passages, chop_files. The shared chop_ prefix accurately groups related operations without introducing inconsistent conventions.
Three tools is a tight, well-scoped surface for a quote-extraction/reranking utility. Each tool covers a distinct input mode or operation, with no filler tools.
The surface covers both core inputs (provided passages and local files) plus reranking, and returns decisions that guide next steps. No obvious operation is missing for the stated chopper/reranker domain.