John's Essentials

photo_shadow_adder

Add Drop Shadow — Add a drop shadow effect to an image, producing a PNG with transparency. [category: photo]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`blur`	No	Shadow edge softness in px. 0 = hard-edged rectangle of a shadow.
`file`	Yes	Image to shadow — JPG, PNG, or WebP only (max 25 MB). BMP is NOT accepted here, unlike most photo tools.
`angle`	No	Which way the shadow falls, in degrees clockwise from the right: 0 moves it right, 90 down, 180 left, 270 up. The default 45 puts it down and to the right, as if lit from the top left.
`opacity`	No	Shadow darkness 0-100. Affects the shadow layer only, never the image itself.
`distance`	No	Shadow offset in px.
`shadow_color`	No	Hex shadow color. Field name is 'shadow_color' — not 'color'.	#000000
`output_format`	No	Leave blank to keep the format it came in as. Only PNG keeps the area around the shadow see-through; JPG and WebP are flattened onto white.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedSep 29, 2026

changedInput schema / properties / angle / default
```
Previous value: -315New value: +45
```

changedInput schema / properties / angle / description

Previous value: -"Shadow direction in degrees."New value: +"Which way the shadow falls, in degrees clockwise from the right: 0 moves it right, 90 down, 180 left, 270 up. The default 45 puts it down and to the right, as if lit from the top left."

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

Added value: +{
+  "of": "shadow",
+  "role": "angle"
+}

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

Added value: +{
+  "of": "shadow",
+  "role": "blur"
+}

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

Added value: +{
+  "of": "shadow",
+  "role": "distance"
+}

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

Added value: +{
+  "max": 100,
+  "of": "shadow",
+  "role": "opacity"
+}

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

Added value: +{
+  "of": "shadow",
+  "role": "format",
+  "see_through": [
+    "png"
+  ]
+}

addedInput schema / properties / shadow_color / x-ui

Added value: +{
+  "draw": {
+    "names": {
+      "aqua": [
+        0,
+        255,
+        255
+      ],
+      "beige": [
+        245,
+        245,
+        220
+      ],
+      "black": [
+        0,
+        0,
+        0
+      ],
+      "blue": [
+        0,
+        0,
+        255
+      ],
+      "brown": [
+        165,
+        42,
+        42
+      ],
+      "crimson": [
+        220,
+        20,
+        60
+      ],
+      "cyan": [
+        0,
+        255,
+        255
+      ],
+      "fuchsia": [
+        255,
+        0,
+        255
+      ],
+      "gold": [
+        255,
+        215,
+        0
+      ],
+      "gray": [
+        128,
+        128,
+        128
+      ],
+      "green": [
+        0,
+        128,
+        0
+      ],
+      "grey": [
+        128,
+        128,
+        128
+      ],
+      "indigo": [
+        75,
+        0,
+        130
+      ],
+      "ivory": [
+        255,
+        255,
+        240
+      ],
+      "khaki": [
+        240,
+        230,
+        140
+      ],
+      "lavender": [
+        230,
+        230,
+        250
+      ],
+      "lime": [
+        0,
+        255,
+        0
+      ],
+      "magenta": [
+        255,
+        0,
+        255
+      ],
+      "maroon": [
+        128,
+        0,
+        0
+      ],
+      "navy": [
+        0,
+        0,
+        128
+      ],
+      "olive": [
+        128,
+        128,
+        0
+      ],
+      "orange": [
+        255,
+        165,
+        0
+      ],
+      "pink": [
+        255,
+        192,
+        203
+      ],
+      "purple": [
+        128,
+        0,
+        128
+      ],
+      "red": [
+        255,
+        0,
+        0
+      ],
+      "salmon": [
+        250,
+        128,
+        114
+      ],
+      "silver": [
+        192,
+        192,
+        192
+      ],
+      "tan": [
+        210,
+        180,
+        140
+      ],
+      "teal": [
+        0,
+        128,
+        128
+      ],
+      "turquoise": [
+        64,
+        224,
+        208
+      ],
+      "violet": [
+        238,
+        130,
+        238
+      ],
+      "white": [
+        255,
+        255,
+        255
+      ],
+      "yellow": [
+        255,
+        255,
+        0
+      ]
+    },
+    "of": "shadow",
+    "role": "color"
+  }
+}

addedInput schema / x-draw

Added value: +{
+  "shadow": {
+    "noun": "shadow",
+    "shape": "shadow",
+    "title": "The shadow"
+  }
+}

Changed1 schema field changedSep 24, 2026
- addedInput schema / properties / output_format / x-ui
```
Added value: +{
+  "unset_label": "Keeps input format"
+}
```
Changed4 schema fields changedSep 23, 2026
- addedInput schema / properties / angle / x-ui
```
Added value: +{
+  "unit": "deg"
+}
```
- addedInput schema / properties / blur / x-ui
```
Added value: +{
+  "unit": "px"
+}
```
- addedInput schema / properties / distance / x-ui
```
Added value: +{
+  "unit": "px"
+}
```
- addedInput schema / properties / opacity / x-ui
```
Added value: +{
+  "unit": "%"
+}
```

Changed2 schema fields changedSep 11, 2026

changedInput schema / properties / output_format / description

Previous value: -"Optional output format."New value: +"Leave blank to keep the format it came in as. Only PNG keeps the area around the shadow see-through; JPG and WebP are flattened onto white."

addedInput schema / properties / output_format / enum
```
Added value: +[
+  "png",
+  "jpg",
+  "webp"
+]
```

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that output is a PNG with transparency, which is mildly inaccurate since output_format defaults to the input format and only PNG preserves transparency — a subtle inconsistency the schema corrects.

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?

One front-loaded sentence with the effect and output stated up front; slightly redundant by restating the title verbatim, plus a category tag, but no significant waste.

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

Completeness4/5

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

For a single-effect image mutation tool, the description plus a fully documented 7-parameter schema and safety annotations gives an agent enough to call it correctly. It lacks only usage routing and a note that non-PNG outputs flatten onto white.

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 coverage is 100% and every parameter (blur, angle, opacity, distance, shadow_color, output_format) is thoroughly documented in the schema. The description adds no parameter detail, so the baseline 3 is appropriate.

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 (add) and resource (drop shadow effect on an image) and names the output artifact. It is clearly distinguishable from photo siblings like photo_add_border or photo_rounded_corners, though it never explicitly differentiates itself from them.

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 guidance on when to use this versus alternatives such as photo_editor, photo_add_border, or photo_rounded_corners, and no prerequisites (e.g. input constraints) stated in the description. Only implied usage from the name.

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?