John's Essentials

analyze_file_diff

Read-only

File Diff — Show a line-by-line diff between two text files (file_a + file_b) or two pasted texts (text_a + text_b). Provide one complete pair. [category: analyze]

Input Schema

TableJSON Schema

Name	Required	Description
`file_a`	No	First file — TXT, CSV, JSON, XML. Send file_a AND file_b together (file mode).
`file_b`	No	Second file.
`strict`	No	Only the first 2,000 lines of each side are compared. Switch on to get an error instead of a comparison that covers part of the files.
`text_a`	No	The BEFORE version. Anything that appears only here is reported as removed.
`text_b`	No	The AFTER version. Anything that appears only here is reported as added.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 26, 2026

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

Previous value: -"Uses the original file instead"New value: +"Leave both texts empty to compare two files"

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

Previous value: -"Uses the updated file instead"New value: +"Leave both texts empty to compare two files"

Changed2 schema fields changedSep 26, 2026
- addedInput schema / properties / text_a / x-ui / multiline
```
Added value: +true
```
- addedInput schema / properties / text_b / x-ui / multiline
```
Added value: +true
```

Changed2 schema fields changedSep 26, 2026

addedInput schema / properties / text_a / x-ui

Added value: +{
+  "unset_label": "Uses the original file instead"
+}

addedInput schema / properties / text_b / x-ui

Added value: +{
+  "unset_label": "Uses the updated file instead"
+}

Changed3 schema fields changedSep 25, 2026
- addedInput schema / properties / file_a / title
```
Added value: +"Original file"
```
- addedInput schema / properties / file_b / title
```
Added value: +"Updated file"
```
- addedInput schema / x-require-one-of
```
Added value: +[
+  [
+    "file_a",
+    "file_b"
+  ],
+  [
+    "text_a",
+    "text_b"
+  ]
+]
```

Changed5 schema fields changedSep 11, 2026

addedInput schema / properties / strict

Added value: +{
+  "default": false,
+  "description": "Only the first 2,000 lines of each side are compared. Switch on to get an error instead of a comparison that covers part of the files.",
+  "title": "Refuse partial answers",
+  "type": "boolean"
+}

changedInput schema / properties / text_a / description

Previous value: -"First text — alternative to the file pair. Send text_a AND text_b together (text mode)."New value: +"The BEFORE version. Anything that appears only here is reported as removed."

addedInput schema / properties / text_a / title
```
Added value: +"Original text"
```

changedInput schema / properties / text_b / description

Previous value: -"Second text."New value: +"The AFTER version. Anything that appears only here is reported as added."

addedInput schema / properties / text_b / title
```
Added value: +"Updated text"
```

First observedSep 5, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already carry the read-only safety profile, so the description's burden is lower. It adds the line-by-line comparison behavior and the pair requirement, but does not disclose operational limits such as the 2,000-line cap (which lives only in the strict parameter description). No contradiction with annotations.

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?

A single front-loaded sentence states the core purpose and the two valid input modes, ending with the key usage constraint 'Provide one complete pair.' No filler; the [category: analyze] tag is minor but does not hurt.

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 two-mode tool with rich per-parameter descriptions and a read-only annotation, the description plus schema fully covers how to invoke the tool correctly. The only gap is that no output format is described, but the line-by-line diff behavior makes the expected result 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 already documents every parameter thoroughly. The description adds useful grouping by naming which parameters belong to file mode vs text mode, but this repeats information already encoded in the parameter descriptions and x-require-one-of. Baseline 3 is appropriate.

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?

Description states a specific action ('Show a line-by-line diff') and the exact resources involved ('two text files' or 'two pasted texts'). It also names the relevant parameter pairs, making it clear this is a text-diff tool rather than the image-diff sibling photo_image_diff.

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

Usage Guidelines4/5

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

Description gives clear usage context: provide one complete pair, either file_a+file_b or text_a+text_b. It does not explicitly name alternatives or exclusions, but the two-mode instruction is enough to guide most calls and is reinforced by the schema's x-require-one-of.

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?