John's Essentials

photo_collage

Photo Collage — Arrange 2-16 images into a smart-cropped collage with aspect-ratio-aware layouts, named magazine templates, or legacy NxM grids. Output: JPG, PNG, WebP, AVIF. [category: photo]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`gap`	No	Gap between cells in px, 0-100.
`files`	Yes	2-16 images — JPG, PNG, WebP, HEIC. The multipart field name is 'files[]' (with brackets).
`layout`	No	A plain grid, written as columns then rows.	2x2
`quality`	No	Output quality; 0 or omitted = engine default.
`bg_color`	No	'white', 'black', 'transparent', or hex (#abc/#aabbcc). Unknown values silently become white; jpg output flattens transparency to white.	white
`template`	No	Named template (layout_mode=template), e.g. ig_post_2x2, ig_story_3_vertical, ig_post_5_magazine. Needed when Layout mode is template: there is no default, and a template-mode run with none chosen, or with fewer photos than the template has places for, is refused with the reason.
`layout_mode`	No	Omit to auto-infer: 'template' present implies template mode, 'layout' implies grid_legacy, otherwise smart.	smart
`aspect_ratio`	No	Output aspect ratio (smart mode).	1:1
`output_width`	No	Older name for the setting above. Set the longest side instead; this is only used if that one is left empty.
`output_format`	No	'jpeg' is accepted as an alias for jpg. png ignores 'quality' (fixed compression).	jpg
`output_long_edge`	No	Output long edge in px.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 24, 2026

changedInput schema / properties / template / description

Previous value: -"Named template (layout_mode=template), e.g. ig_post_2x2, ig_story_3_vertical, ig_post_5_magazine."New value: +"Named template (layout_mode=template), e.g. ig_post_2x2, ig_story_3_vertical, ig_post_5_magazine. Needed when Layout mode is template: there is no default, and a template-mode run with none chosen, or with fewer photos than the template has places for, is refused with the reason."

changedInput schema / properties / template / x-ui / unset_label

Previous value: -"No template"New value: +"Choose a template"

Changed1 schema field changedSep 24, 2026
- addedInput schema / properties / template / x-ui / unset_label
```
Added value: +"No template"
```
Changed3 schema fields changedSep 23, 2026
- addedInput schema / properties / gap / x-ui
```
Added value: +{
+  "unit": "px"
+}
```
- addedInput schema / properties / output_long_edge / x-ui
```
Added value: +{
+  "unit": "px"
+}
```
- addedInput schema / properties / output_width / x-ui
```
Added value: +{
+  "unit": "px"
+}
```

Changed15 schema fields changedSep 11, 2026

addedInput schema / properties / aspect_ratio / default
```
Added value: +"1:1"
```

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

Added value: +{
+  "layout_mode": [
+    "smart",
+    "grid_legacy"
+  ]
+}

addedInput schema / properties / layout / default
```
Added value: +"2x2"
```

changedInput schema / properties / layout / description

Previous value: -"Legacy NxM grid, e.g. 2x2, 3x3 (layout_mode=grid_legacy)."New value: +"A plain grid, written as columns then rows."

addedInput schema / properties / layout / enum

Added value: +[
+  "1x2",
+  "2x1",
+  "2x2",
+  "2x3",
+  "3x2",
+  "3x3",
+  "4x4"
+]

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

Added value: +{
+  "layout_mode": [
+    "grid_legacy"
+  ]
+}

addedInput schema / properties / output_long_edge / default
```
Added value: +1200
```

changedInput schema / properties / output_width / description

Previous value: -"Legacy alias for output_long_edge."New value: +"Older name for the setting above. Set the longest side instead; this is only used if that one is left empty."

addedInput schema / properties / quality / default
```
Added value: +90
```
changedInput schema / properties / quality / minimum
```
Previous value: -0New value: +1
```

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

Added value: +{
+  "output_format": [
+    "jpg",
+    "webp",
+    "avif"
+  ]
+}

changedInput schema / properties / template / description

Previous value: -"Named template (layout_mode=template), e.g. ig_post_2x2, ig_story_3_vertical, magazine_5_hero."New value: +"Named template (layout_mode=template), e.g. ig_post_2x2, ig_story_3_vertical, ig_post_5_magazine."

addedInput schema / properties / template / enum

Added value: +[
+  "ig_post_2x2",
+  "ig_post_hero_3",
+  "ig_post_5_magazine",
+  "ig_story_3_vertical",
+  "ig_story_hero_4",
+  "ig_carousel_4_split",
+  "pinterest_3_stack",
+  "landscape_3up_equal",
+  "landscape_hero_2_offset",
+  "landscape_film_strip",
+  "square_diptych",
+  "square_triptych_top_2_bottom_1"
+]

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

Added value: +{
+  "layout_mode": [
+    "template"
+  ]
+}

addedInput schema / properties / template / x-ui

Added value: +{
+  "labels": {
+    "ig_carousel_4_split": "Carousel — quad split",
+    "ig_post_2x2": "Instagram post — 2x2",
+    "ig_post_5_magazine": "Magazine — 5 photos",
+    "ig_post_hero_3": "Instagram post — hero + 3",
+    "ig_story_3_vertical": "Story — 3 stacked",
+    "ig_story_hero_4": "Story — hero + 4 strip",
+    "landscape_3up_equal": "Landscape — 3 equal columns",
+    "landscape_film_strip": "Landscape — 5 film strip",
+    "landscape_hero_2_offset": "Landscape — hero + 2 stacked",
+    "pinterest_3_stack": "Pinterest — 3 stack",
+    "square_diptych": "Diptych — side by side",
+    "square_triptych_top_2_bottom_1": "Triptych — 2 over 1"
+  }
+}

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 are minimal (readOnlyHint false, destructiveHint false, openWorldHint false), and the description adds some behavioral context: smart-cropping, aspect-ratio awareness, and output formats. It does not disclose side effects, how output is returned, or what happens to source files, though destructiveHint false already covers non-destruction.

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?

One compact sentence leads with the action, then packs the key constraints (2-16 images, layout types, output formats) and a category tag. No filler or repetition.

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 high-complexity tool with 11 parameters, the schema is rich enough to cover invocation details, and the description supplies the missing selection-level context: input count, layout families, and output formats. It does not describe the return representation, and there is no output schema, so it is not a perfect 5.

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 11 parameters. The description only adds high-level layout context ('smart-cropped,' 'magazine templates,' 'legacy NxM grids') rather than parameter-specific semantics, which keeps it at 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 opens with a specific verb and resource: 'Arrange 2-16 images into a smart-cropped collage.' It also distinguishes the operation from sibling photo tools by naming layout modes (smart, magazine templates, legacy grids) and output formats, so an agent can tell this is the multi-image collage tool rather than photo_crop or photo_image_overlay.

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

Usage Guidelines3/5

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

The description implies usage by stating the input count and layout modes, but it never explicitly says when to prefer this tool over siblings or when not to use it. There are no alternative tool names or exclusion conditions, so guidance is left to inference.

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?