diff --git a/dev/proxy-kustomization.yaml b/dev/proxy-kustomization.yaml
index 59036f9..9dee05f 100644
--- a/dev/proxy-kustomization.yaml
+++ b/dev/proxy-kustomization.yaml
@@ -40,7 +40,13 @@ spec:
       VECTORDB_HOST: llm-dev-vectordb
       VECTORDB_PORT: "6379"
       RATE_LIMIT_GLOBAL_TOKENS_PER_MINUTE: "500000"
-      RATE_LIMIT_PER_CLIENT_TOKENS_PER_MINUTE: "50000"
+      # Doubled from 50000. A tool-calling agent re-sends the whole tool
+      # result on every iteration of its loop, so one question against a
+      # tool that returns a full collection (list-products is ~23 KB) can
+      # burn the old budget in three turns and answer 429 mid-reasoning.
+      # Pagination on those tools is the real fix; this buys room until
+      # then, and stays well inside the global ceiling.
+      RATE_LIMIT_PER_CLIENT_TOKENS_PER_MINUTE: "100000"
       # Looked up after consumer.yaml's llm-anonymous KongConsumer first
       # reconciled — config.anonymous needs the real Consumer ID, not the
       # username (Konnect stores it as a literal string otherwise, silently