diff --git a/stacks/qwen3.5-122b/compose.yaml b/stacks/qwen3.5-122b/compose.yaml
index a414c6b..ba77ebc 100644
--- a/stacks/qwen3.5-122b/compose.yaml
+++ b/stacks/qwen3.5-122b/compose.yaml
@@ -40,7 +40,11 @@ services:
       - MAX_NUM_BATCHED_TOKENS=${QWEN35_MAX_NUM_BATCHED_TOKENS:-32768}
       # --reasoning-parser qwen3 surfaces <think>…</think> as reasoning_content;
       # the thinking on/off itself is per-request (litellm chat_template_kwargs).
-      - VLLM_EXTRA_ARGS=--reasoning-parser qwen3 --enable-chunked-prefill
+      # --enable-auto-tool-choice + --tool-call-parser: Qwen3.5 emits XML tool calls
+      # <tool_call><function=NAME><parameter=K>V</parameter></function></tool_call>
+      # (NOT Hermes JSON), so the parser is qwen3_xml. Without these flags vLLM never
+      # parses tool calls (tool-calling is broken). The bjk110 repo command omitted them.
+      - VLLM_EXTRA_ARGS=--reasoning-parser qwen3 --enable-chunked-prefill --enable-auto-tool-choice --tool-call-parser qwen3_xml
       - NVIDIA_VISIBLE_DEVICES=0
       - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
       - VLLM_API_KEY=${API_KEY:-}