John's Essentials

pdf_to_excel_inspect

Read-only

PDF to Excel Inspector — Non-destructive scan of a PDF's tables before converting: per-table row/column counts, confidence flags, warnings. [category: pdf]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file`	Yes	The PDF to scan (multipart field 'file', 25MB cap). Runs real extraction but returns JSON metadata only — nothing is converted.
`pages`	No	Optional page range
`engine`	No	Table detection engine; invalid values fall back to auto.	auto
`ocrLang`	No	Accepted but ignored by the inspector - it never runs OCR. Run PDF OCR first, then inspect.	eng
`ocrFirst`	No	Accepted but ignored by the inspector — run pdf_ocr first, then inspect.
`tableIndexes`	No	Accepted but ignored by the inspector - its whole job is to report every table so you can choose indexes on PDF to Excel afterwards.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 26, 2026
- addedInput schema / properties / pages / title
```
Added value: +"Pages to read"
```
- addedInput schema / properties / pages / x-ui / no_recall
```
Added value: +true
```
- addedInput schema / properties / pages / x-ui / page_select
```
Added value: +{}
```
Changed2 schema fields changedSep 26, 2026
- addedInput schema / properties / pages / x-ui
```
Added value: +{
+  "unset_label": "All pages"
+}
```
- addedInput schema / properties / tableIndexes / x-ui
```
Added value: +{
+  "unset_label": "All tables"
+}
```

Changed6 schema fields changedSep 11, 2026

changedInput schema / properties / ocrFirst / description

Previous value: -"Run OCR before table extraction (scanned PDFs)."New value: +"Accepted but ignored by the inspector — run pdf_ocr first, then inspect."

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

Added value: +{
+  "engine": [
+    "__never"
+  ]
+}

changedInput schema / properties / ocrLang / description

Previous value: -"OCR language (Tesseract code)."New value: +"Accepted but ignored by the inspector - it never runs OCR. Run PDF OCR first, then inspect."

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

Added value: +{
+  "engine": [
+    "__never"
+  ]
+}

changedInput schema / properties / tableIndexes / description

Previous value: -"Comma-separated 0-based table indexes to keep. Empty = all tables."New value: +"Accepted but ignored by the inspector - its whole job is to report every table so you can choose indexes on PDF to Excel afterwards."

addedInput schema / properties / tableIndexes / x-show-when
```
Added value: +{
+  "engine": [
+    "__never"
+  ]
+}
```

First observedSep 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The annotations declare readOnlyHint=true and the description reinforces it with 'non-destructive' and 'nothing is converted.' It goes beyond the flag by revealing that real extraction runs but only JSON metadata is returned, and that several schema parameters are accepted but ignored — behavior an agent cannot infer from annotations alone.

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?

The description is one efficient sentence that front-loads the purpose and outputs, with no repetition of the title or category tag. Detailed parameter behavior is correctly delegated to the schema rather than duplicated in the description.

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

Completeness5/5

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

For a read-only inspector with a rich schema and readOnlyHint annotation, the description covers input, purpose, output contents, and side-effect guarantee. Although there is no output schema, the explicit list of returned metadata (counts, flags, warnings) is enough for an agent to decide whether and how to call the tool.

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 main description does not need to document individual parameters and the baseline of 3 applies. The main description adds no parameter-specific detail, though the schema's own field descriptions cover file size, page ranges, engine fallback, and ignored options well.

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 leads with a specific operation: a non-destructive scan of a PDF's tables before conversion, with concrete outputs (row/column counts, confidence flags, warnings). It clearly distinguishes the inspect step from the actual conversion by stating that nothing is converted, which separates it from pdf_to_excel and pdf_to_excel_batch.

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

Usage Guidelines5/5

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

It positions the tool explicitly as a pre-conversion step ('before converting') and the schema reinforces the workflow: inspect first, use the reported table indexes to choose selection in PDF to Excel afterwards, and run pdf_ocr first if OCR is needed. The accepted-but-ignored OCR and tableIndexes parameters make exclusions explicit rather than implicit.

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?