Scored across 37 tools
Most tools have distinct purposes, but there is slight overlap between pdf_extract_pages and pdf_split, and between pdf_overlay_pdf and pdf_watermark. Descriptions help disambiguate, so agents can generally select correctly.
All tools follow the same consistent pattern: prefix 'pdf_' followed by a descriptive verb_noun in snake_case (e.g., pdf_add_image, pdf_merge, pdf_validate). No mixing of conventions.
37 tools is on the higher side, but each covers a distinct PDF operation, from creation to manipulation to validation. The set feels comprehensive rather than bloated, though a few tools could be simplified.
The toolset covers a wide range of PDF lifecycle operations: create, read, edit, annotate, merge/split, form handling, security, metadata, and more. The only notable gap is OCR for scanned documents, which is beyond typical scope. The redaction tool is visual-only, but the description warns clearly.