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.
`text`	No	Defaults to 'John's Essentials' when omitted — always pass your own. A leading '@' is stripped.	John's Essentials
`color`	No	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.	#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	Points. 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.

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

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this is a non-destructive write. The description adds nothing behavioral beyond that — it does not say whether the original file is overwritten or a new file is produced, nor what the tool returns. Adequate against the annotation-provided safety profile, but thin.

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?

A single front-loaded sentence with the verb and resource first, followed by the configurable knobs. Efficient, though the trailing '[category: photo]' tag is mild noise rather than useful content.

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, the description is only just sufficient: the schema thoroughly documents parameters and the annotations cover the safety profile, but no output schema exists and the description never states whether the source photo is modified in place or a new file is emitted. That is a meaningful omission for a write operation.

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 itself carries rich per-parameter semantics (opacity integer parsing, gravity case-sensitivity, font_size silent reset, stroke auto behavior). The description only restates that position/opacity/font size are configurable and adds no syntax or default detail beyond the schema, so the baseline of 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?

The description gives a specific verb+resource ('Add Image Watermark — Overlay a text watermark on a photo') and names the configurable dimensions (position, opacity, font size). It clearly conveys what the tool does, but never acknowledges the closely named sibling media_add_watermark (or pdf_watermark), so an agent must infer that this one is for raster photos rather than video/PDF.

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?

No when-to-use or when-not guidance is given. With media_add_watermark and pdf_watermark in the sibling list, the absence of any routing statement ('use this for JPG/PNG/H...; use media_add_watermark for video') leaves the agent to guess. The '[category: photo]' tag is the only weak disambiguator.

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?