refactor: Address AI review feedback

Code improvements:
- Remove unused frozen_cols parameter from _expand_range_with_headers
- Add include_header to log messages for better debugging
- Unify default value (True) between public API and internal methods

Documentation improvements:
- Add metadata_only to parameter tables (usage.md, usage_ja.md)
- Add comprehensive usage example for metadata_only mode
- Show recommended workflow: inspect structure first, then fetch data

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

Author: k-ibaraki

docs/usage.md

@@ -188,6 +188,7 @@ The `sharepoint_excel` tool allows you to read and search Excel files in SharePo
 | `cell_range` | str \| None | None | Cell range (e.g., "A1:D10") |
 | `include_formatting` | bool | False | Include formatting information |
 | `include_header` | bool | True | Auto-detect and separate header rows using `freeze_panes` |
+| `metadata_only` | bool | False | Return only file and worksheet metadata without cell contents |
 
 ### Basic Workflow
 
@@ -310,6 +311,48 @@ result = sharepoint_excel(
 - Set `include_header=False` to return legacy `rows` format
 ```
 
+#### 7. Metadata-Only Mode (File Structure Inspection)
+```python
+# Get only file structure without data rows
+result = sharepoint_excel(
+    file_path="/sites/finance/Shared Documents/large-report.xlsx",
+    metadata_only=True
+)
+```
+
+**Metadata-Only Response:**
+```json
+{
+  "file_path": "/sites/finance/Shared Documents/large-report.xlsx",
+  "sheets": [{
+    "name": "Sheet1",
+    "freeze_panes": "B2",
+    "frozen_rows": 1,
+    "frozen_cols": 1,
+    "dimensions": "A1:E1000",
+    "header_rows": [
+      [
+        {"value": "Product", "coordinate": "A1"},
+        {"value": "Price", "coordinate": "B1"},
+        {"value": "Stock", "coordinate": "C1"}
+      ]
+    ],
+    "data_rows": []
+  }]
+}
+```
+
+**Use Cases:**
+- Inspect large file structure before fetching data
+- Understand what headers exist in each sheet
+- Determine the necessary `cell_range` before retrieving full data
+- Reduce token usage
+
+**Recommended Workflow:**
+1. Use `metadata_only=True` to inspect file structure
+2. Identify the required range
+3. Fetch actual data with specific `cell_range`
+
 ### JSON Output Format
 
 #### Read Mode (Default)

docs/usage_ja.md

@@ -188,6 +188,7 @@ SHAREPOINT_SITE_NAME=@onedrive,sales-team,customer-portal
 | `cell_range` | str \| None | None | セル範囲（例: "A1:D10"） |
 | `include_formatting` | bool | False | 書式情報を含めるか |
 | `include_header` | bool | True | ヘッダー行を自動検出して分離するか（`freeze_panes`を使用） |
+| `metadata_only` | bool | False | メタデータ（シート名やセル範囲など）のみを返し、セル内容は取得しないかどうか |
 
 ### 基本的なワークフロー
 
@@ -310,6 +311,48 @@ result = sharepoint_excel(
 - `include_header=False`を指定すると、従来の`rows`形式で返す
 ```
 
+#### 7. メタデータのみ取得（ファイル構造の確認）
+```python
+# データ行を除外してファイル構造のみを取得
+result = sharepoint_excel(
+    file_path="/sites/finance/Shared Documents/large-report.xlsx",
+    metadata_only=True
+)
+```
+
+**メタデータのみのレスポンス:**
+```json
+{
+  "file_path": "/sites/finance/Shared Documents/large-report.xlsx",
+  "sheets": [{
+    "name": "Sheet1",
+    "freeze_panes": "B2",
+    "frozen_rows": 1,
+    "frozen_cols": 1,
+    "dimensions": "A1:E1000",
+    "header_rows": [
+      [
+        {"value": "商品名", "coordinate": "A1"},
+        {"value": "価格", "coordinate": "B1"},
+        {"value": "在庫", "coordinate": "C1"}
+      ]
+    ],
+    "data_rows": []
+  }]
+}
+```
+
+**ユースケース:**
+- 大きなファイルの構造を事前に確認
+- どのシートにどんなヘッダーがあるかを把握
+- 必要な`cell_range`を決定してから本データを取得
+- トークン使用量の削減
+
+**推奨ワークフロー:**
+1. `metadata_only=True`でファイル構造を確認
+2. 必要な範囲を特定
+3. `cell_range`を指定して本データを取得
+
 ### JSON出力形式
 
 #### 読み取りモード（デフォルト）

src/sharepoint_excel.py

@@ -119,7 +119,7 @@ def parse_to_json(
         logger.info(
             f"Parsing Excel file: {file_path} "
             f"(include_formatting={include_formatting}, sheet={sheet_name}, range={cell_range}, "
-            f"metadata_only={metadata_only})"
+            f"include_header={include_header}, metadata_only={metadata_only})"
         )
 
         try:
@@ -166,7 +166,7 @@ def _parse_sheet(
         sheet,
         include_formatting: bool,
         cell_range: str | None = None,
-        include_header: bool = False,
+        include_header: bool = True,
         metadata_only: bool = False,
     ) -> dict[str, Any]:
         """
@@ -216,7 +216,7 @@ def _parse_sheet(
             # セル範囲を拡張してヘッダーを含める
             if include_header and frozen_rows > 0:
                 header_range, data_range = self._expand_range_with_headers(
-                    cell_range, frozen_rows, frozen_cols
+                    cell_range, frozen_rows
                 )
 
                 # ヘッダー範囲がある場合は取得
@@ -410,15 +410,14 @@ def _parse_freeze_panes(self, freeze_panes: str | None) -> tuple[int, int]:
             return (0, 0)
 
     def _expand_range_with_headers(
-        self, cell_range: str, frozen_rows: int, frozen_cols: int
+        self, cell_range: str, frozen_rows: int
     ) -> tuple[str | None, str]:
         """
         cell_rangeを固定範囲を含むように拡張
 
         Args:
             cell_range: セル範囲（例: "A5:D10"）
             frozen_rows: 固定行数
-            frozen_cols: 固定列数
 
         Returns:
             (header_range, data_range)のタプル