docs: clarify MLX usage and tool-call validation

Use direct Hugging Face loading commands and document the search-only one-shot smoke-test scope.

README.md

@@ -1,19 +1,21 @@
 ---
 license: apache-2.0
+language: en
 library_name: mlx
 base_model: Alibaba-NLP/WebSailor-3B
 base_model_revision: b317a15261674d83d851f0a14761840583bb9dce
 tags:
-- mlx
-- mlx-lm
-- 8-bit
-- web-agent
+  - mlx
+  - mlx-lm
+  - 8-bit
+  - web-agent
+  - web-search
 pipeline_tag: text-generation
 ---
 
 # WebSailor-3B-MLX-8bit-community
 
-Unofficial community MLX conversion of [Alibaba-NLP/WebSailor-3B](https://huggingface.co/Alibaba-NLP/WebSailor-3B).
+Unofficial community MLX conversion of [Alibaba-NLP/WebSailor-3B](https://huggingface.co/Alibaba-NLP/WebSailor-3B) for Apple Silicon.
 
 This repository is not an official Alibaba-NLP or Hugging Face release and does not imply endorsement by the original authors.
 
@@ -27,36 +29,56 @@ This repository is not an official Alibaba-NLP or Hugging Face release and does
 - Conversion tool: `mlx-lm 0.31.2` with `mlx 0.31.1`
 - Original license: Apache-2.0; see [`LICENSE`](./LICENSE)
 
+Install MLX-LM with:
+
+```bash
+pip install -U mlx-lm
+```
+
 The conversion command was:
 
 ```bash
 HF_HUB_DISABLE_XET=1 mlx_lm.convert \
   --hf-path Alibaba-NLP/WebSailor-3B \
   --mlx-path ./WebSailor-3B-MLX-8bit \
-  --quantize --q-bits 8 --q-group-size 64
+  --quantize \
+  --q-bits 8 \
+  --q-group-size 64
 ```
 
 ## Local usage
 
+MLX-LM can resolve the Hugging Face repository ID directly:
+
 ```bash
+pip install -U mlx-lm
+
 mlx_lm.generate \
-  --model ./WebSailor-3B-MLX-8bit \
+  --model eunjay/WebSailor-3B-MLX-8bit-community \
   --prompt "Reply with one short sentence." \
   --max-tokens 64
 ```
 
-The conversion was tested locally with `mlx_lm.generate` on Apple Silicon. The model weights alone do not browse the web; web-search or browser tool calls require an external tool/backend and an agent loop.
+For a local checkout, replace the repository ID with `./WebSailor-3B-MLX-8bit`.
+
+The model weights alone do not browse the web; web-search or browser tool calls require an external tool/backend and an agent loop.
+
+## Tool calling and web-search scope
 
-## Tool calling with `mlx_lm.server`
+The original WebSailor-3B agent harness uses both `search` and `visit` tools through WebAgent. This MLX conversion was validated only with a one-shot `search` tool-call smoke test; the full WebSailor/WebAgent `search` + `visit` harness was not run against this conversion.
 
-Use the original WebSailor search tool contract: the function name is `search` and `query` is an array of strings. Add an explicit JSON-format instruction to the system message so the model emits a parser-compatible call:
+For the smoke test, an explicit JSON-format instruction was supplied so the model emitted a parser-compatible call:
 
 ```text
 If you need the search tool, output exactly one valid JSON object between <tool_call> and </tool_call>. Use double-quoted keys and this shape: {"name":"search","arguments":{"query":["query text"]}}. Never output YAML labels such as name: or arguments:.
 ```
 
-With that instruction, the local OpenAI-compatible MLX server returned `finish_reason: "tool_calls"` and parsed the generated call successfully. The search service itself remains external and must execute the requested queries.
+The local OpenAI-compatible MLX server parsed that single call successfully. The search service itself remains external and must execute the requested query. This result is not validation of the complete WebSailor search agent or its `visit` flow.
+
+## Compatibility note
+
+Hugging Face may display Pi, Hermes, or OpenClaw connection examples automatically for compatible serving endpoints. Those examples indicate endpoint connectivity, not validation of WebSailor's search-agent behavior. Tool-call markers and parsers can vary across MLX-LM versions, so treat the result above as a **one-shot smoke test** and verify the full agent harness before production use.
 
 ## Attribution
 
-Please retain the original model attribution and Apache-2.0 license when redistributing this conversion. This repository contains the converted weights and supporting tokenizer/configuration files; it is not a replacement for the original model card or project code.
+Please retain the original model attribution and Apache-2.0 license when redistributing this conversion. This repository contains converted weights and supporting tokenizer/configuration files; it is not a replacement for the [original model card](https://huggingface.co/Alibaba-NLP/WebSailor-3B) or project code.