DatasetID   string `json:"dataset_id" jsonschema:"required,Dataset ID (12 characters)"`
	CSVPath     string `json:"csv_path" jsonschema:"required,Absolute path to CSV file"`
	LogFilePath string `json:"log_file_path" jsonschema:"required,Absolute path for progress log"`

	DatasetID   string `json:"dataset_id" jsonschema:"required,description=Dataset ID (12 characters)"`
	CSVPath     string `json:"csv_path" jsonschema:"required,description=Absolute path to CSV file. Format: location_name,location_id,directory_path,date_range,sample_rate,file_count (header required). date_range becomes cluster name. Example: 'Site A',abc123,/path/files,20240101-20240107,48000,100"`
	LogFilePath string `json:"log_file_path" jsonschema:"required,description=Absolute path for progress log file (monitors import progress)"`

**CSV Format for bulk_file_import:**
```csv
location_name,location_id,directory_path,date_range,sample_rate,file_count
"Test Location","testloc12345","/path/to/test/files","test-2024","48000","10"
```
**Required columns (in order):**
1. `location_name` - Display name (string, can have spaces)
2. `location_id` - 12-character ID (must exist in database)
3. `directory_path` - Absolute path to WAV files
4. `date_range` - Becomes cluster name (any string)
5. `sample_rate` - Sample rate in Hz (integer)
6. `file_count` - Expected count (integer, informational)
**Verify results with SQL:**
```sql
-- Check clusters created
SELECT name FROM cluster WHERE location_id = 'testloc12345';
-- Check files imported
SELECT COUNT(*) FROM file WHERE cluster_id IN (
  SELECT id FROM cluster WHERE location_id = 'testloc12345'
);
```

		Description: "Batch import WAV files across multiple locations/clusters using a CSV file. Auto-creates clusters if needed, logs progress to file for monitoring, and returns summary statistics. Synchronous/fail-fast execution.",

		Description: "Batch import WAV files across multiple locations/clusters using a CSV file. CSV must have columns (in order): location_name, location_id, directory_path, date_range, sample_rate, file_count. Auto-creates clusters using date_range as cluster name. Logs progress to file for monitoring. Synchronous/fail-fast execution.",

  - **Input**: CSV file with columns: location_name, location_id, directory_path, date_range, sample_rate, file_count

  - **Input**: CSV file (see format below)

  **CSV Format:**
  - **Header required:** First row must contain column names
  - **Columns (in order):**
    1. `location_name` - Human-readable location name (string, can have spaces)
    2. `location_id` - 12-character location ID from database (must exist)
    3. `directory_path` - Absolute path to folder containing WAV files
    4. `date_range` - Cluster name (e.g., "20240101-20240107" or any string)
    5. `sample_rate` - Sample rate in Hz (integer, e.g., 8000, 48000, 250000)
    6. `file_count` - Expected file count (integer, informational only)
  
  **Important:**
  - `date_range` becomes the cluster name in the database
  - If cluster already exists for location+date_range, it will be reused
  - All `location_id` values must exist in the database (use `execute_sql` to query)
  - Paths should be absolute (relative paths may fail)
  
  **Example CSV:**
  ```csv
  location_name,location_id,directory_path,date_range,sample_rate,file_count
  "MOK RW 05","Ucfh8ng4DuEa","/media/david/Data/MOK RW 05","20240706-20240714","8000","432"
  "MOK RW 06","rDmmSPsJvNtD","/media/david/Data/MOK RW 06","20240706-20240714","8000","432"
  "mokas__01","EsDkvXosAp4C","/media/david/Data/mokas__01","20240520-20240528","8000","432"
  ```
  
  **Tool Call Example:**
  ```json
  {
    "name": "bulk_file_import",
    "arguments": {
      "dataset_id": "abc123xyz789",
      "csv_path": "/path/to/import.csv",
      "log_file_path": "/path/to/progress.log"
    }
  }
  ```