John's Essentials

pdf_watermark

Add PDF Watermark — STAMP or watermark a PDF: overlay text or an image across every page (or selected pages) — the tool for stamping DRAFT, CONFIDENTIAL, PAID, APPROVED, COPY or any wording onto a document, marking pages, branding them, or adding a logo overlay. Watermark type is chosen by the 'mode' field. [category: pdf]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file`	Yes	Input PDF (filename must end in .pdf)
`mode`	No	Watermark type. 'image' requires the imageFile field — presence of an image alone does NOT switch modes.	text
`text`	No	Watermark text (used when mode=text).	CONFIDENTIAL
`tile`	No	Repeat the watermark in a tiled pattern.
`color`	No	Hex color #rgb or #rrggbb (mode=text).	#808080
`pages`	No	Comma-separated page numbers e.g. '1,3,5'. Empty = all pages.
`scale`	No	Size multiplier. With tile=true only values in (0,1] count (fraction of page) — anything else silently tiles at 0.3.
`opacity`	No	0-1 float; non-numeric resets to 0.3, but out-of-range values reach the PDF engine and 500. NOT a percent.
`fontSize`	No	Point size on the page (mode=text only). Non-integer input silently resets to 48.
`position`	No	Long names like 'bottom-right' are NOT recognized and silently fall back to c. ml/mr work (folded to engine anchors l/r).	c
`rotation`	No	Whole degrees only — a decimal string like '45.5' silently resets to 45.
`imageFile`	No	Watermark image — PNG, JPG, or SVG. REQUIRED when mode=image; ignored otherwise.
`fontFamily`	No	Outside the enum it silently becomes Helvetica. All three are Latin-1 — non-Latin text is refused 400 (use mode=image).	Helvetica
`outputFilename`	No	Optional custom output filename.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 5, 2026

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only convey read/destructive hints, so the description adds useful behavioral context: it overlays text or an image, can target every or selected pages, and mode selects the type. It does not disclose output/return behavior or whether the input file is modified, though the rich schema covers many quirks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and readable, but the first sentence partly repeats the tool name, and the list of example words (DRAFT, CONFIDENTIAL, PAID, APPROVED, COPY) is more verbose than necessary. The category tag is minor metadata and could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter tool with no output schema, the description establishes selection and high-level behavior well, and the schema covers parameter specifics. It leaves gaps around what the tool returns and how output files are handled, so it is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema carries the parameter documentation burden. The description only restates that 'mode' picks the watermark type, which is already in the schema, adding little beyond the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb/resource pair: stamp or watermark a PDF, and details the overlay of text or images across every page or selected pages. It clearly distinguishes this from sibling PDF operations like removing watermarks or adding headers/footers, even without naming them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear, concrete use cases ('stamping DRAFT, CONFIDENTIAL, PAID, APPROVED, COPY...', branding, logo overlay), so an agent knows when to choose it. It does not explicitly name alternatives or state when not to use it, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All John's Essentials tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0

Disambiguation2/5

Multiple tool pairs are near-identical: octopus_mkdir/octopus_make_folder and octopus_move/octopus_move_file are literal duplicates, analyze_hash/generate_hash both compute hashes, convert_word_to_pdf overlaps convert_document, and photo_compress/photo_compress_to_size plus pdf_thumbnails/pdf_to_images have fuzzy boundaries. The descriptions are detailed and cross-reference each other helpfully, but at 144 tools an agent will regularly misselect.

Naming Consistency3/5

The dominant {category}_{verb}_{object} snake_case pattern (pdf_*, photo_*, convert_*, analyze_*, media_*) is largely consistent and predictable. However, outliers like chatwithyourpdf and describe_image break the category-prefix convention, and the octopus namespace mixes bare verbs (read, write, mkdir) with verb_noun forms (make_folder, move_file, search_meta) inconsistently.

Tool Count2/5

144 tools is an extreme count for any MCP server. The broad scope (PDF, photo, video, audio, conversion, analysis, generation, file storage, web, e-sign) justifies some volume, but the count is inflated by batch and inspect variants (pdf_to_excel + batch + inspect), duplicate tools, and overlapping converters. An agent faces an overwhelming selection surface.

Completeness4/5

Per-domain coverage is remarkably deep: PDF spans merge/split/compress/protect/unlock/metadata/OCR/watermark and bidirectional conversion; photo covers editing, format conversion, face handling, OCR, and collage; file storage has full CRUD plus search. Minor gaps exist (no audio transcription, no video metadata editing, no deletion of PDF pages is actually covered via pdf_delete_pages) but the surface has no dead ends for its declared domains.

Resources

Need Help?