# Redact personal information

- Human page: https://happytails.ai/en/privacy-tools/redact-personal-information/
- Markdown: https://happytails.ai/en/privacy-tools/redact-personal-information.md
- Structured JSON: https://happytails.ai/agents/en/privacy-tools/redact-personal-information/index.json
- Visibility: public

## Tool capabilities

| Property | Value |
| --- | --- |
| Tool ID | `redact-personal-information` |
| Category | privacy-tools |
| Implementation | Registered implementation. Registration alone is not a production-quality guarantee. |
| Browser execution | Use the visible action or interactive controls. |
| Browser processing | Server required |
| HTTP API | /api/v1/tools/redact-personal-information/run |
| Browser-agent interface | run_current_tool |

### Implementation notes

Suggest redactions in English text using a local entity model and contact patterns. Review names, emails, phone numbers and street addresses in the JSON preview. Private details may be missed and public text may be flagged. Up to 16,000 characters. This does not guarantee anonymization.

### Inputs and settings

Text input: Your text.

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

```text
Type or paste your input…
```

Up to 1,000,000 characters. Review the settings before running.

No additional settings are declared for this tool.

### HTTP contract

API calls process supplied data on the server. The website origin is `https://happytails.ai`. Server API hosting is not connected on the public website yet. Use your local server origin to test these requests.

```http
POST https://happytails.ai/api/v1/tools/redact-personal-information/run
Content-Type: application/json
```

[Detailed operation reference](https://happytails.ai/en/api/tools/redact-personal-information.md) · [Shared API guide](https://happytails.ai/en/api.md)

#### Limits

| Limit | Value |
| --- | --- |
| request_bytes | 31457280 |
| input_characters | 1000000 |
| files_bytes | 20971520 |
| max_files | 0 |
| timeout_seconds | 90 |

#### Complete input schema

```json
{
  "type": "object",
  "additionalProperties": false,
  "properties": {
    "input": {
      "type": "string",
      "maxLength": 1000000,
      "default": "",
      "description": "Plain text input. File tools use files instead unless otherwise documented."
    },
    "options": {
      "type": "object",
      "additionalProperties": false,
      "properties": {}
    }
  }
}
```

#### Complete output schema

```json
{
  "type": "object",
  "required": [
    "tool",
    "result"
  ],
  "properties": {
    "tool": {
      "type": "string"
    },
    "result": {
      "type": "object",
      "required": [
        "text",
        "files"
      ],
      "properties": {
        "text": {
          "type": [
            "string",
            "null"
          ]
        },
        "data": {
          "description": "Parsed JSON when the textual result is JSON."
        },
        "name": {
          "type": "string"
        },
        "mime": {
          "type": "string"
        },
        "files": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "name",
              "mime",
              "bytes",
              "base64"
            ],
            "properties": {
              "name": {
                "type": "string"
              },
              "mime": {
                "type": "string"
              },
              "bytes": {
                "type": "integer"
              },
              "base64": {
                "type": "string",
                "contentEncoding": "base64"
              }
            }
          }
        }
      }
    }
  }
}
```

#### Error and retry handling

Failures return a non-200 status and `error.code` plus `error.message`. Correct invalid input before retrying; retry server-busy responses with bounded backoff. Returned files contain Base64 data, not persistent download URLs. Decode and inspect the output before treating conversion as successful. See the shared API guide for the complete status and timeout rules.

### 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

Suggest personal-information spans with deterministic pattern checks plus optional model assistance; let users approve each redaction; export plain text; do not claim complete anonymization.

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

### Complete machine-readable capability record

```json
{
  "id": "redact-personal-information",
  "category": "privacy-tools",
  "built": true,
  "requirements": "Suggest personal-information spans with deterministic pattern checks plus optional model assistance; let users approve each redaction; export plain text; do not claim complete anonymization.",
  "implementation": {
    "fields": [],
    "files": false,
    "accept": "",
    "multiple": false,
    "input": true,
    "processing": "Server required",
    "native": true,
    "ai": false,
    "maxFileBytes": 20971520,
    "note": "Suggest redactions in English text using a local entity model and contact patterns. Review names, emails, phone numbers and street addresses in the JSON preview. Private details may be missed and public text may be flagged. Up to 16,000 characters. This does not guarantee anonymization.",
    "extra": true,
    "experience": {
      "automatic": false,
      "single": false,
      "label": "Your text",
      "placeholder": "Type or paste your input…",
      "help": "Up to 1,000,000 characters. Review the settings before running.",
      "action": null
    },
    "mode": "explicit",
    "interactive": false
  },
  "execution": "POST /api/v1/tools/redact-personal-information/run",
  "api": {
    "id": "redact-personal-information",
    "name": "Redact personal information",
    "category": "privacy-tools",
    "description": "Suggest redactions in English text using a local entity model and contact patterns.",
    "notes": "Suggest redactions in English text using a local entity model and contact patterns. Review names, emails, phone numbers and street addresses in the JSON preview. Private details may be missed and public text may be flagged. Up to 16,000 characters. This does not guarantee anonymization.",
    "human_path": "/en/privacy-tools/redact-personal-information/",
    "method": "POST",
    "endpoint": "/api/v1/tools/redact-personal-information/run",
    "schema_url": "/api/v1/tools/redact-personal-information",
    "input_schema": {
      "type": "object",
      "additionalProperties": false,
      "properties": {
        "input": {
          "type": "string",
          "maxLength": 1000000,
          "default": "",
          "description": "Plain text input. File tools use files instead unless otherwise documented."
        },
        "options": {
          "type": "object",
          "additionalProperties": false,
          "properties": {}
        }
      }
    },
    "output_schema": {
      "type": "object",
      "required": [
        "tool",
        "result"
      ],
      "properties": {
        "tool": {
          "type": "string"
        },
        "result": {
          "type": "object",
          "required": [
            "text",
            "files"
          ],
          "properties": {
            "text": {
              "type": [
                "string",
                "null"
              ]
            },
            "data": {
              "description": "Parsed JSON when the textual result is JSON."
            },
            "name": {
              "type": "string"
            },
            "mime": {
              "type": "string"
            },
            "files": {
              "type": "array",
              "items": {
                "type": "object",
                "required": [
                  "name",
                  "mime",
                  "bytes",
                  "base64"
                ],
                "properties": {
                  "name": {
                    "type": "string"
                  },
                  "mime": {
                    "type": "string"
                  },
                  "bytes": {
                    "type": "integer"
                  },
                  "base64": {
                    "type": "string",
                    "contentEncoding": "base64"
                  }
                }
              }
            }
          }
        }
      }
    },
    "processing": "Server; self-hosted native engine, no external conversion service",
    "limits": {
      "request_bytes": 31457280,
      "input_characters": 1000000,
      "files_bytes": 20971520,
      "max_files": 0,
      "timeout_seconds": 90
    }
  },
  "agent_processing": "Server; self-hosted native engine, no external conversion service",
  "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

Suggest redactions in English text using a local entity model and contact patterns.

## How to use Redact personal information

1. Enter your text in the input field.
2. Review the settings, then choose Run Redact personal information.
3. Review the result, then use Copy result or a download link when available.

## What to expect

Suggest redactions in English text using a local entity model and contact patterns. Suggest redactions in English text using a local entity model and contact patterns. Review names, emails, phone numbers and street addresses in the JSON preview. Private details may be missed and public text may be flagged. Up to 16,000 characters. This does not guarantee anonymization.