remove_watermarks Leave feedback

remove_watermarks removes watermarks and saves the result as <name>_unwatermarked.<ext>. Pass textFilter to remove only the ones containing given text — “remove the DRAFT mark but keep the logo”. Example prompt: “Remove the DRAFT watermark now that it is approved”.

Tool description (as the AI agent sees it):

Removes existing watermarks from a document and saves the cleaned copy as ‘_unwatermarked.’. Supports PDF, DOCX, XLSX, PPTX, PNG, JPG, and 50+ more document and image formats. Call this tool whenever the user asks to remove / strip / clean / delete watermarks from a document. If textFilter is supplied, only watermarks whose text contains that substring (case-insensitive) are removed; otherwise ALL watermarks are removed. Do NOT pre-check whether the file exists — just pass the filename the user provided. Returns a saved-path message (‘Removed watermark(s) from “”’) and the download URL or storage path. If no matching watermarks are found, the original document is saved unchanged with a message starting ‘No matching watermarks found in’. On failure, the response text starts with ‘Watermark removal failed for’ followed by the underlying exception type, message, and inner-exception chain.

{
  "name": "remove_watermarks",
  "arguments": {
    "file": {
      "filePath": "contract.pdf"
    },
    "textFilter": "DRAFT"
  }
}

A saved-path message naming the cleaned file.

What comes out is what the engine can identify as a watermark object. Content that merely looks like a watermark — flattened into an image, or drawn as ordinary page text — stays. Run search_watermarks first if the answer matters.

On failure the text starts with Watermark removal failed for, followed by the exception type and message.

• “Remove the DRAFT watermark now that this is approved.”
• “Strip every watermark from these files.”
• “Take out the old logo watermark but leave the confidentiality mark.”

See it used end-to-end: Find and remove watermarks.