grammarly_optimize_text
Analyze text for AI detection and plagiarism scores, then rewrite content to meet specified thresholds for humanized output.
Instructions
Get AI detection and plagiarism scores from Grammarly, optionally rewriting text with the configured LLM to reduce scores. Modes: 'score_only' (scores only), 'analyze' (scores + recommendations), 'optimize' (iterative rewriting to meet thresholds).
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| mode | No | score_only gets scores, analyze interprets them, optimize rewrites to meet thresholds. | optimize |
| max_ai_percent | No | Target maximum AI detection percentage. | |
| max_plagiarism_percent | No | Target maximum plagiarism percentage. | |
| max_iterations | No | Maximum optimization iterations in optimize mode. | |
| tone | No | Desired tone of the final text. | neutral |
| domain_hint | No | Short description of the domain (e.g., 'university essay'). | |
| custom_instructions | No | Extra constraints (e.g., preserve citations, do not change code blocks). | |
| proxy_country_code | No | ISO 3166-1 alpha-2 country code for proxy (e.g., 'us', 'gb'). | |
| response_format | No | Output format: 'json' for structured data, 'markdown' for human-readable. | json |
| max_steps | No | Maximum browser automation steps per scoring task (default 25). Prevents runaway tasks. |