John's Essentials

pdf_page_numbers

Add Page Numbers — Add page numbers to a PDF at a specified position (top/bottom, left/center/right). [category: pdf]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file`	Yes	PDF up to 25MB. Password-protected input is rejected 400 — run pdf_unlock first.
`color`	No	Hex color #rrggbb.	#333333
`start`	No	The number printed on the first numbered page.
`format`	No	How each number is written on the page.	Page {page}
`fontSize`	No	Does NOT clamp — anything below 6 or above 72 silently RESETS to the default 10.
`position`	No	Where the number sits on the page.	bc
`skipLast`	No	Skip numbering the last page.
`pageRange`	No	Only number these pages, e.g. '2-5,8'. Empty = all pages.
`skipFirst`	No	Skip numbering the first page.
`fontFamily`	No	Outside the enum it silently becomes Helvetica. Latin-1 fonts — a 'format' template with CJK/Cyrillic/emoji is refused 400.	Helvetica
`romanNumerals`	No	Render numbers as roman numerals.
`outputFilename`	No	Optional custom output filename.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 26, 2026
- addedInput schema / properties / pageRange / title
```
Added value: +"Pages to number"
```
- addedInput schema / properties / pageRange / x-ui
```
Added value: +{
+  "no_recall": true,
+  "page_select": {}
+}
```
Changed1 schema field changedSep 23, 2026
- addedInput schema / properties / fontSize / x-ui
```
Added value: +{
+  "unit": "pt"
+}
```

Changed4 schema fields changedSep 11, 2026

changedInput schema / properties / position / description

Previous value: -"Short codes ONLY: bc=bottom-center, bl=bottom-left, br=bottom-right, tc=top-center, tl=top-left, tr=top-right. Long names like 'bottom-right' are NOT recognized and silently fall back to bottom-center."New value: +"Where the number sits on the page."

addedInput schema / properties / position / x-ui

Added value: +{
+  "labels": {
+    "bc": "Bottom centre",
+    "bl": "Bottom left",
+    "br": "Bottom right",
+    "tc": "Top centre",
+    "tl": "Top left",
+    "tr": "Top right"
+  }
+}

changedInput schema / properties / start / description

Previous value: -"Starting number. Field name is 'start' — not 'start_number'."New value: +"The number printed on the first numbered page."

changedInput schema / properties / start / maximum
```
Previous value: -999999New value: +999
```

Changed3 schema fields changedSep 11, 2026

changedInput schema / properties / format / description

Previous value: -"Number template with {page} and {pages} tokens."New value: +"How each number is written on the page."

addedInput schema / properties / format / enum

Added value: +[
+  "Page {page}",
+  "{page}",
+  "{page} of {pages}",
+  "- {page} -"
+]

addedInput schema / properties / format / x-ui

Added value: +{
+  "labels": {
+    "- {page} -": "- 1 -",
+    "Page {page}": "Page 1",
+    "{page}": "1",
+    "{page} of {pages}": "1 of 10"
+  }
+}

First observedSep 5, 2026

TDQS

B3.2/5.0

Behavior3/5

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

The annotations already cover the safety profile with readOnlyHint=false and destructiveHint=false, so the description is not required to repeat those basics. It adds a bit of behavioral context about positioning, but it does not say whether a new PDF is produced, what gets returned, or what happens on invalid input.

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?

The description is compact and front-loaded: one sentence states the operation and its main option, followed by a short category tag. There is minor redundancy because 'Add Page Numbers' appears in both the title and the sentence, but no meaningful bloat.

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?

With 12 parameters and no output schema, the description alone is thin, especially around return values, output file behavior, and error conditions. However, the complete parameter schema and annotations partially compensate, making the tool callable but not fully self-explanatory.

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 fully documents all 12 parameters, including color, start, format, position, and romanNumerals. The prose only re-states the position dimension already visible in the schema enum, adding no new parameter semantics beyond the structured data.

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 is specific: 'Add page numbers to a PDF at a specified position (top/bottom, left/center/right)' names the verb, resource, and key customization. It does not explicitly distinguish itself from sibling tools like pdf_header_footer or pdf_watermark, so it stops short of full sibling differentiation.

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?

There is no guidance on when to use this tool versus alternatives such as pdf_header_footer or pdf_watermark. It also does not mention that password-protected input should be sent to pdf_unlock first, leaving selection and prerequisites to the agent's 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?