John's Essentials

photo_watermark

Add Image Watermark — Overlay a text watermark on a photo with configurable position (ImageMagick gravity names), opacity, and font size. [category: photo]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file`	Yes	JPG, PNG, WebP, GIF, BMP, HEIC, TIFF. Max 25 MB. Output keeps the input format, except that a HEIC or HEIF photo comes back as a JPG.
`text`	Yes	The words stamped onto the photo. Required; there is no default. A leading '@' is removed.
`color`	No	A hex colour, or one of white, black, gray, grey, red, orange, yellow, green, blue, cyan, magenta, purple, pink, brown. Anything else falls back to white.	#ffffff
`opacity`	No	INTEGER percent 0-100 — a fraction like 0.5 parses as 0 (invisible watermark).
`position`	No	Case-sensitive ImageMagick gravity name — 'center' (lowercase) or 'top-left' are NOT recognized and silently fall back to SouthEast.	SouthEast
`font_size`	No	How big the lettering is, measured in PIXELS of the photo rather than points on a page: the words are drawn straight onto the bitmap, so the same number gives the same size here, on the Signature Generator and on PDF to Images. Out-of-range values (<6 or >500) silently reset to 36 — no error returned.
`stroke_color`	No	The outline behind the text, which is what keeps a watermark readable over a white dress or a black suit. Leave it unset and it is picked for you - black behind a light colour, white behind a dark one. Same colour names as above.
`stroke_width`	No	How thick the outline behind the text is. Leave it on auto and it scales with the text size. 0 turns the outline off; otherwise a whole number up to 20 - anything larger is treated as 20.	auto

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedSep 29, 2026

addedInput schema / properties / color / x-ui

Added value: +{
+  "draw": {
+    "names": {
+      "black": [
+        0,
+        0,
+        0
+      ],
+      "blue": [
+        37,
+        99,
+        235
+      ],
+      "brown": [
+        120,
+        63,
+        4
+      ],
+      "cyan": [
+        6,
+        182,
+        212
+      ],
+      "gray": [
+        128,
+        128,
+        128
+      ],
+      "green": [
+        22,
+        163,
+        74
+      ],
+      "grey": [
+        128,
+        128,
+        128
+      ],
+      "magenta": [
+        192,
+        38,
+        211
+      ],
+      "orange": [
+        234,
+        88,
+        12
+      ],
+      "pink": [
+        236,
+        72,
+        153
+      ],
+      "purple": [
+        147,
+        51,
+        234
+      ],
+      "red": [
+        220,
+        38,
+        38
+      ],
+      "white": [
+        255,
+        255,
+        255
+      ],
+      "yellow": [
+        250,
+        204,
+        21
+      ]
+    },
+    "of": "mark",
+    "role": "color"
+  }
+}

addedInput schema / properties / font_size / x-ui / draw

Added value: +{
+  "leading_number": true,
+  "measure": "font-px",
+  "of": "mark",
+  "out_of_range": "default",
+  "role": "size"
+}

addedInput schema / properties / opacity / x-ui / draw

Added value: +{
+  "leading_number": true,
+  "max": 100,
+  "of": "mark",
+  "role": "opacity"
+}

addedInput schema / properties / position / x-ui / draw

Added value: +{
+  "cells": {
+    "Center": "mc",
+    "East": "mr",
+    "North": "tc",
+    "NorthEast": "tr",
+    "NorthWest": "tl",
+    "South": "bc",
+    "SouthEast": "br",
+    "SouthWest": "bl",
+    "West": "ml"
+  },
+  "of": "mark",
+  "role": "anchor"
+}

addedInput schema / properties / stroke_color / x-ui / draw

Added value: +{
+  "light_luma": 140,
+  "names": {
+    "black": [
+      0,
+      0,
+      0
+    ],
+    "blue": [
+      37,
+      99,
+      235
+    ],
+    "brown": [
+      120,
+      63,
+      4
+    ],
+    "cyan": [
+      6,
+      182,
+      212
+    ],
+    "gray": [
+      128,
+      128,
+      128
+    ],
+    "green": [
+      22,
+      163,
+      74
+    ],
+    "grey": [
+      128,
+      128,
+      128
+    ],
+    "magenta": [
+      192,
+      38,
+      211
+    ],
+    "orange": [
+      234,
+      88,
+      12
+    ],
+    "pink": [
+      236,
+      72,
+      153
+    ],
+    "purple": [
+      147,
+      51,
+      234
+    ],
+    "red": [
+      220,
+      38,
+      38
+    ],
+    "white": [
+      255,
+      255,
+      255
+    ],
+    "yellow": [
+      250,
+      204,
+      21
+    ]
+  },
+  "of": "mark",
+  "role": "outline_color"
+}

addedInput schema / properties / stroke_width / x-ui

Added value: +{
+  "draw": {
+    "auto": {
+      "max": 8,
+      "min": 1,
+      "per": 18
+    },
+    "leading_number": true,
+    "max": 20,
+    "of": "mark",
+    "role": "outline_width"
+  }
+}

addedInput schema / properties / text / x-ui

Added value: +{
+  "draw": {
+    "face": "noto-sans-condensed",
+    "of": "mark",
+    "role": "text"
+  }
+}

addedInput schema / x-draw

Added value: +{
+  "mark": {
+    "noun": "watermark",
+    "shape": "stamp",
+    "title": "Watermark on the photo"
+  }
+}

Changed1 schema field changedSep 26, 2026
- addedInput schema / properties / stroke_color / x-ui
```
Added value: +{
+  "unset_label": "Picked to stand out from the text"
+}
```

Changed1 schema field changedSep 25, 2026

changedInput schema / properties / file / description

Previous value: -"JPG, PNG, WebP, GIF, BMP, HEIC, TIFF. Max 25 MB. Output keeps the input format."New value: +"JPG, PNG, WebP, GIF, BMP, HEIC, TIFF. Max 25 MB. Output keeps the input format, except that a HEIC or HEIF photo comes back as a JPG."

Changed1 schema field changedSep 24, 2026

changedInput schema / properties / text / description

Previous value: -"The words stamped onto the photo. Required, and there is no default: a step nobody opened used to stamp our own company name onto the customer's picture. A leading '@' is stripped."New value: +"The words stamped onto the photo. Required; there is no default. A leading '@' is removed."

Changed3 schema fields changedSep 24, 2026

changedInput schema / properties / color / description

Previous value: -"A hex colour, or one of white, black, gray, red, orange, yellow, green, blue, cyan, magenta, purple, pink, brown. Anything else falls back to white."New value: +"A hex colour, or one of white, black, gray, grey, red, orange, yellow, green, blue, cyan, magenta, purple, pink, brown. Anything else falls back to white."

changedInput schema / properties / font_size / description

Previous value: -"Points. Out-of-range values (<6 or >500) silently reset to 36 — no error returned."New value: +"How big the lettering is, measured in PIXELS of the photo rather than points on a page: the words are drawn straight onto the bitmap, so the same number gives the same size here, on the Signature Generator and on PDF to Images. Out-of-range values (<6 or >500) silently reset to 36 — no error returned."

changedInput schema / properties / font_size / x-ui / unit
```
Previous value: -"pt"New value: +"px"
```

Changed5 schema fields changedSep 23, 2026

addedInput schema / properties / font_size / x-ui
```
Added value: +{
+  "unit": "pt"
+}
```
addedInput schema / properties / opacity / x-ui
```
Added value: +{
+  "unit": "%"
+}
```
removedInput schema / properties / text / default
```
Removed value: -"John's Essentials"
```

changedInput schema / properties / text / description

Previous value: -"Defaults to 'John's Essentials' when omitted — always pass your own. A leading '@' is stripped."New value: +"The words stamped onto the photo. Required, and there is no default: a step nobody opened used to stamp our own company name onto the customer's picture. A leading '@' is stripped."

changedInput schema / required

Previous value: -[
-  "file"
-]New value: +[
+  "file",
+  "text"
+]

Changed4 schema fields changedSep 11, 2026

addedInput schema / properties / color

Added value: +{
+  "default": "#ffffff",
+  "description": "A hex colour, or one of white, black, gray, red, orange, yellow, green, blue, cyan, magenta, purple, pink, brown. Anything else falls back to white.",
+  "title": "Watermark colour",
+  "type": "string"
+}

addedInput schema / properties / position / x-ui

Added value: +{
+  "labels": {
+    "Center": "Middle centre",
+    "East": "Middle right",
+    "North": "Top centre",
+    "NorthEast": "Top right",
+    "NorthWest": "Top left",
+    "South": "Bottom centre",
+    "SouthEast": "Bottom right",
+    "SouthWest": "Bottom left",
+    "West": "Middle left"
+  }
+}

addedInput schema / properties / stroke_color

Added value: +{
+  "description": "The outline behind the text, which is what keeps a watermark readable over a white dress or a black suit. Leave it unset and it is picked for you - black behind a light colour, white behind a dark one. Same colour names as above.",
+  "title": "Outline colour",
+  "type": "string"
+}

addedInput schema / properties / stroke_width

Added value: +{
+  "default": "auto",
+  "description": "How thick the outline behind the text is. Leave it on auto and it scales with the text size. 0 turns the outline off; otherwise a whole number up to 20 - anything larger is treated as 20.",
+  "title": "Outline thickness",
+  "type": "string"
+}

First observedSep 5, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the note that positions follow ImageMagick gravity names, which is mildly useful behavioral context, but says nothing about whether the source photo is modified or a new file is returned, and no rate/size limits beyond what the schema already states.

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

Conciseness5/5

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

A single front-loaded sentence with the action, the resource, and the tunable dimensions; nothing is wasted and the bracketed category tag is trivial overhead.

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 an 8-parameter mutation tool with no output schema, the description should say what comes back (a new image file? a URL?) and confirm the original is untouched. It covers the input side adequately but leaves the entire return contract to inference.

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%, and the schema entries are unusually rich (fallback behavior for color, opacity integer parsing, case-sensitive gravity names, silent reset of out-of-range font sizes). The description only names three of the eight parameters at a high level, adding little beyond the schema, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource ("Overlay a text watermark on a photo") and names the configurable axes, so the agent knows exactly what the tool produces. It does not, however, explicitly distinguish itself from the similarly-named siblings media_add_watermark and pdf_watermark, leaving the agent to infer that "photo" means raster images.

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

Usage Guidelines2/5

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

The description gives no when-to-use guidance, no prerequisites, and no mention of the alternative watermark tools (media_add_watermark, pdf_watermark) that appear in the sibling list. The agent must infer applicability purely from the word "photo".

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?