# Data dictionary generator

- Human page: https://happytails.ai/en/data-tools/data-dictionary-generator/
- Markdown: https://happytails.ai/en/data-tools/data-dictionary-generator.md
- Structured JSON: https://happytails.ai/agents/en/data-tools/data-dictionary-generator/index.json
- Visibility: public

## Tool capabilities

| Property | Value |
| --- | --- |
| Tool ID | `data-dictionary-generator` |
| Category | data-tools |
| Implementation | Registered implementation. Registration alone is not a production-quality guarantee. |
| Browser execution | Automatic updates after valid input or file selection. |
| Browser processing | Browser; see tool notes for network behavior. |
| HTTP API | Not callable through HTTP. |
| Browser-agent interface | run_current_tool |

### Implementation notes

Runs locally on your device. CSV requires unique nonempty headers. Up to 1,000,000 characters, 10,000 data records and 100,000 cells across inputs, with 100 columns. Quoted multiline cells are supported. Each JSON settings field is limited to 100,000 characters. Output files are bounded to 4,000,000 characters. Diagnostic reports contain at most 500 findings and disclose the omitted count. Download an editable CSV field catalogue containing observed types, empty counts, distinct counts and your descriptions. Raw example cell values are not included. Protect spreadsheet cells prefixes formula-like values, including negative numbers, with an apostrophe. Choose Preserve original cells only for a trusted import workflow.

### Inputs and settings

Text input: CSV data.

Example or placeholder shown in the interface (not a validated fixture):

```text
id,name
1,Alpha
2,Beta
```

Paste CSV data with unique column headers. Quoted multiline cells are supported. Results update as you type. Up to 1,000,000 characters.

| Setting | Meaning | Control type | Default | Constraints |
| --- | --- | --- | --- | --- |
| `separator` | Input CSV separator | select | "," | Allowed: ,, ;, 	 |
| `descriptions` | Field descriptions (JSON) | textarea | "{}" |  |
| `outputSafety` | CSV output cells | select | "Protect spreadsheet cells" | Allowed: Protect spreadsheet cells, Preserve original cells |

### Browser-agent workflow

1. Open the human page in a browser that supports WebMCP.
2. Discover the interface exposed by that page; use its actual schema.
3. Select files on the page first when the tool requires files.
4. Call `run_current_tool` with valid input and settings.
5. Inspect the returned result or error and the displayed output. Retrieve files from the displayed download links.

Calls do not automatically copy or download results. Browser permissions still apply. Interface availability alone is not proof of successful execution.

### Planning specification

The dictionary contains observed types, empty counts, distinct counts and optional descriptions. It excludes raw example values. Inference cannot recover undocumented business meanings. Up to 1,000,000 characters, 10,000 data records, 100 columns and 100,000 cells across the sources. Files for multi-source tools are limited to 4,000,000 bytes total. Reports retain at most 500 diagnostic findings and state any omitted count. CSV and JSON outputs are limited to 4,000,000 characters.

This describes intended requirements. Use the implementation notes, interface schema and observed output to determine current support.

### Complete machine-readable capability record

```json
{
  "id": "data-dictionary-generator",
  "category": "data-tools",
  "built": true,
  "requirements": "The dictionary contains observed types, empty counts, distinct counts and optional descriptions. It excludes raw example values. Inference cannot recover undocumented business meanings. Up to 1,000,000 characters, 10,000 data records, 100 columns and 100,000 cells across the sources. Files for multi-source tools are limited to 4,000,000 bytes total. Reports retain at most 500 diagnostic findings and state any omitted count. CSV and JSON outputs are limited to 4,000,000 characters.",
  "implementation": {
    "fields": [
      {
        "key": "separator",
        "label": "Input CSV separator",
        "value": ",",
        "type": "select",
        "values": [
          ",",
          ";",
          "\t"
        ]
      },
      {
        "key": "descriptions",
        "label": "Field descriptions (JSON)",
        "value": "{}",
        "type": "textarea",
        "help": "An object mapping exact column names to editable descriptions, for example {\"id\":\"Customer identifier\"}."
      },
      {
        "key": "outputSafety",
        "label": "CSV output cells",
        "value": "Protect spreadsheet cells",
        "type": "select",
        "values": [
          "Protect spreadsheet cells",
          "Preserve original cells"
        ]
      }
    ],
    "live": true,
    "presentation": "metrics",
    "note": "Runs locally on your device. CSV requires unique nonempty headers. Up to 1,000,000 characters, 10,000 data records and 100,000 cells across inputs, with 100 columns. Quoted multiline cells are supported. Each JSON settings field is limited to 100,000 characters. Output files are bounded to 4,000,000 characters. Diagnostic reports contain at most 500 findings and disclose the omitted count. Download an editable CSV field catalogue containing observed types, empty counts, distinct counts and your descriptions. Raw example cell values are not included. Protect spreadsheet cells prefixes formula-like values, including negative numbers, with an apostrophe. Choose Preserve original cells only for a trusted import workflow.",
    "experience": {
      "automatic": true,
      "single": false,
      "inputMaxLength": 1000000,
      "inputMode": "text",
      "label": "CSV data",
      "placeholder": "id,name\n1,Alpha\n2,Beta",
      "help": "Paste CSV data with unique column headers. Quoted multiline cells are supported. Results update as you type. Up to 1,000,000 characters.",
      "action": null
    },
    "mode": "automatic",
    "interactive": false
  },
  "execution": "Browser interface",
  "api": null,
  "browser_agent": {
    "supported": true,
    "name": "run_current_tool",
    "discovery": "WebMCP on the human page in a supporting browser",
    "verification": "See audit/API-AUDIT.md; availability is not verification"
  }
}
```

## Page guide

Turn CSV headers and observed values into an editable field catalogue with descriptions.

How can we improve this tool?

Report a problem or share an idea.

Please leave out private information. Your message and the tool name go to our team via PostHog.

### How to use Data dictionary generator

1. Paste a representative CSV export.
2. Add descriptions as a JSON object keyed by the exact column names.
3. Download the field dictionary as CSV and edit it in your spreadsheet.

## Useful next steps

- [CSV type profiler](https://happytails.ai/en/data-tools/csv-type-profiler/) ([Markdown](https://happytails.ai/en/data-tools/csv-type-profiler.md))

- [Dataset coverage matrix](https://happytails.ai/en/data-tools/dataset-coverage-matrix/) ([Markdown](https://happytails.ai/en/data-tools/dataset-coverage-matrix.md))

## Prepare the source

Paste a representative CSV export.

### Choose the matching rules

Add descriptions as a JSON object keyed by the exact column names.

### Review and keep the result

Download the field dictionary as CSV and edit it in your spreadsheet. The dictionary contains observed types, empty counts, distinct counts and optional descriptions. It excludes raw example values. Inference cannot recover undocumented business meanings.