Tool Search plugin
The Tool Search plugin keeps a large tool catalog out of the client’s context. On a route with Tool Search, tools/list returns three gateway tools instead of the route’s real tools:
search_toolranks the real tools by meaning against a query.get_toolreturns one tool’s input schema.execute_toolcalls a real tool by name.
The gateway ranks tools with embeddings from an OpenAI-compatible embedding service that you configure.
Where it runs
Configuration
Results returned when the client doesn’t give a usable limit. At least 1, and not above result_limit_max.
The maximum number of results.
The maximum characters in each tool summary.
The embedding service.
The service’s base URL. The gateway calls POST <base_url>/embeddings with input and model, in the OpenAI format.
The embedding model.
The vector length the model returns, at least 1. Vectors of any other length count as a failure.
A named secret reference for the service’s API key, sent as Authorization: Bearer. Raw env:// and file:// references are refused.
The time limit for each call to the embedding service.
The total time to embed tools that don’t have a vector yet.
Optional. With quantize and cache_scope, it only labels the vector index.
Tools per embedding call.
Example
On an Enterprise data plane, the Helm chart also deploys an embedding service, fabric-gateway-embedder, that serves the BAAI/bge-small-en-v1.5 model with 384 dimensions. For the embedder settings that use it, see Run the tool-search embedder.

