John's Essentials

pdf_images_to_pdf

Images to PDF — Combine multiple images (JPG, PNG, TIFF) into a single PDF document. [category: pdf]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`files`	Yes	Input files (JPG, JPEG, PNG, WEBP)
`margin`	No	White border around each picture, in points - 72 points is one inch. A margin so large that nothing is left for the picture is ignored rather than refused.
`fitMode`	No	How each picture sits on the page.	contain
`pageSize`	No	Fit makes every page exactly the size of its own picture, so a phone photo becomes a page yards across. Any fixed size gives one uniform, printable document.	fit
`autoOrient`	No	Turn photos the right way up using the camera's own rotation tag. On by default — switch it off only if you want the raw pixels exactly as stored.
`orientation`	No	Leave blank to follow the page size you picked.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 11, 2026

addedInput schema / properties / autoOrient

Added value: +{
+  "default": true,
+  "description": "Turn photos the right way up using the camera's own rotation tag. On by default — switch it off only if you want the raw pixels exactly as stored.",
+  "type": "boolean"
+}

changedInput schema / properties / files / description

Previous value: -"Input files (JPG, PNG, TIFF)"New value: +"Input files (JPG, JPEG, PNG, WEBP)"

addedInput schema / properties / fitMode

Added value: +{
+  "default": "contain",
+  "description": "How each picture sits on the page.",
+  "enum": [
+    "contain",
+    "fill"
+  ],
+  "type": "string",
+  "x-show-when": {
+    "pageSize": [
+      "a4",
+      "a4-landscape",
+      "letter",
+      "letter-landscape",
+      "legal",
+      "legal-landscape",
+      "a3",
+      "a3-landscape",
+      "a5",
+      "a5-landscape",
+      "tabloid",
+      "tabloid-landscape"
+    ]
+  },
+  "x-ui": {
+    "labels": {
+      "contain": "Show the whole picture",
+      "fill": "Fill the page (crops the edges)"
+    }
+  }
+}

addedInput schema / properties / margin

Added value: +{
+  "default": 0,
+  "description": "White border around each picture, in points - 72 points is one inch. A margin so large that nothing is left for the picture is ignored rather than refused.",
+  "maximum": 200,
+  "minimum": 0,
+  "type": "integer",
+  "x-show-when": {
+    "pageSize": [
+      "a4",
+      "a4-landscape",
+      "letter",
+      "letter-landscape",
+      "legal",
+      "legal-landscape",
+      "a3",
+      "a3-landscape",
+      "a5",
+      "a5-landscape",
+      "tabloid",
+      "tabloid-landscape"
+    ]
+  }
+}

addedInput schema / properties / orientation

Added value: +{
+  "description": "Leave blank to follow the page size you picked.",
+  "enum": [
+    "portrait",
+    "landscape",
+    "auto"
+  ],
+  "type": "string",
+  "x-show-when": {
+    "pageSize": [
+      "a4",
+      "a4-landscape",
+      "letter",
+      "letter-landscape",
+      "legal",
+      "legal-landscape",
+      "a3",
+      "a3-landscape",
+      "a5",
+      "a5-landscape",
+      "tabloid",
+      "tabloid-landscape"
+    ]
+  },
+  "x-ui": {
+    "labels": {
+      "auto": "Match each picture",
+      "landscape": "Landscape",
+      "portrait": "Portrait"
+    }
+  }
+}

addedInput schema / properties / pageSize

Added value: +{
+  "default": "fit",
+  "description": "Fit makes every page exactly the size of its own picture, so a phone photo becomes a page yards across. Any fixed size gives one uniform, printable document.",
+  "enum": [
+    "fit",
+    "a4",
+    "a4-landscape",
+    "letter",
+    "letter-landscape",
+    "legal",
+    "legal-landscape",
+    "a3",
+    "a3-landscape",
+    "a5",
+    "a5-landscape",
+    "tabloid",
+    "tabloid-landscape"
+  ],
+  "type": "string",
+  "x-ui": {
+    "labels": {
+      "a3": "A3 portrait",
+      "a3-landscape": "A3 landscape",
+      "a4": "A4 portrait",
+      "a4-landscape": "A4 landscape",
+      "a5": "A5 portrait",
+      "a5-landscape": "A5 landscape",
+      "fit": "Fit the page to the picture",
+      "legal": "Legal portrait",
+      "legal-landscape": "Legal landscape",
+      "letter": "Letter portrait",
+      "letter-landscape": "Letter landscape",
+      "tabloid": "Tabloid portrait",
+      "tabloid-landscape": "Tabloid landscape"
+    }
+  }
+}

First observedSep 5, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already establish this is a non-read-only, non-destructive, closed-world operation, so safety is covered. The description adds nothing further: no page ordering, output naming, or handling of malformed images. With annotations carrying the safety profile, a 3 is the ceiling.

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

Conciseness3/5

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

The single sentence is front-loaded and mentions formats, but the trailing "[category: pdf]" tag is internal metadata noise that earns no place in agent-facing text. Size is fine; content is slightly padded.

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 a 6-parameter tool with full schema coverage and clear annotations, the description is minimally viable. It never explains output ordering, file naming, or error behavior on unreadable inputs, and gives no routing against convert_jpg_to_pdf.

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 each parameter (margin, fitMode, pageSize, autoOrient, orientation) already carries a rich description including defaults, ranges, and UI labels. The description adds no parameter meaning, so 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 (combine) and resource (multiple images into a single PDF) with supported formats named. It does not, however, distinguish itself from the close sibling convert_jpg_to_pdf, which handles the same JPG-to-PDF conversion for a single file.

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-to-use guidance is given, and the obvious alternative convert_jpg_to_pdf (and convert_document) is never mentioned. The agent must infer that multiple input files route here.

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?