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	The wording stamped across each page.	CONFIDENTIAL
`tile`	No	Repeat the watermark in a tiled pattern.
`color`	No	Colour of the lettering. Hex, #rgb or #rrggbb.	#808080
`pages`	No	Which pages to stamp, 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	Height of the lettering in points.
`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	Lettering style. Latin alphabet only — for other scripts stamp an image instead.	Helvetica
`outputFilename`	No	Optional custom output filename.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 26, 2026

changedInput schema / properties / pages / description

Previous value: -"Comma-separated page numbers e.g. '1,3,5'. Empty = all pages."New value: +"Which pages to stamp, e.g. '1-3,5'. Empty = all pages."

addedInput schema / properties / pages / title
```
Added value: +"Pages to stamp"
```

addedInput schema / properties / pages / x-ui

Added value: +{
+  "no_recall": true,
+  "page_select": {}
+}

Changed1 schema field changedSep 24, 2026
- addedInput schema / properties / imageFile / x-show-when
```
Added value: +{
+  "mode": [
+    "image"
+  ]
+}
```
Changed2 schema fields changedSep 23, 2026
- addedInput schema / properties / fontSize / x-ui
```
Added value: +{
+  "unit": "pt"
+}
```
- addedInput schema / properties / rotation / x-ui
```
Added value: +{
+  "unit": "deg"
+}
```

Changed8 schema fields changedSep 11, 2026

changedInput schema / properties / color / description

Previous value: -"Hex color #rgb or #rrggbb (mode=text)."New value: +"Colour of the lettering. Hex, #rgb or #rrggbb."

addedInput schema / properties / color / x-show-when
```
Added value: +{
+  "mode": [
+    "text"
+  ]
+}
```

changedInput schema / properties / fontFamily / description

Previous value: -"Outside the enum it silently becomes Helvetica. All three are Latin-1 — non-Latin text is refused 400 (use mode=image)."New value: +"Lettering style. Latin alphabet only — for other scripts stamp an image instead."

addedInput schema / properties / fontFamily / x-show-when
```
Added value: +{
+  "mode": [
+    "text"
+  ]
+}
```

changedInput schema / properties / fontSize / description

Previous value: -"Point size on the page (mode=text only). Non-integer input silently resets to 48."New value: +"Height of the lettering in points."

addedInput schema / properties / fontSize / x-show-when
```
Added value: +{
+  "mode": [
+    "text"
+  ]
+}
```

changedInput schema / properties / text / description

Previous value: -"Watermark text (used when mode=text)."New value: +"The wording stamped across each page."

addedInput schema / properties / text / x-show-when

Added value: +{
+  "mode": [
+    "text"
+  ]
+}

First observedSep 5, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already indicate readOnlyHint=false (a write operation). The description adds some behavioral quirks like silent fallbacks for invalid position, rotation, and scale values, which is useful. But it doesn't state whether the original file is modified or a new file is created, or what the output contains, leaving some behavior undisclosed.

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

Conciseness4/5

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

The description is front-loaded with the main purpose and use cases, but it's somewhat verbose with redundant examples (DRAFT, CONFIDENTIAL, PAID, etc.). It could be tightened without losing clarity, but the structure is logical and readable.

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?

With 14 parameters and no output schema, the description should explain what the tool returns or how the watermarked file is delivered. It doesn't mention the output at all. While the schema covers parameters well, the description lacks information about the result of the operation, which is a notable gap for a complex tool.

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 already documents all 14 parameters. The description adds minimal extra meaning (e.g., that mode selects watermark type, and imageFile is required for image mode) but these are already present in the schema. It doesn't enrich parameter understanding beyond the schema.

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 clearly states it adds a PDF watermark/stamp, overlaying text or an image on pages. It lists specific use cases (DRAFT, CONFIDENTIAL, etc.) and distinguishes itself from siblings like pdf_remove_watermark, media_add_watermark, and photo_watermark by the resource (PDF) and action.

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 gives explicit usage context (stamping documents, branding, logo overlay) and even provides a conditional guideline: for non-Latin scripts, use an image instead of text. However, it doesn't explicitly mention alternatives by name or state when NOT to use this tool beyond the script note.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?