Skip to main content
Glama

HALOWERK: Compares two versions of a document — PDF, DOCX, ODT, HTML, Markdown or plain te

doc_diff
Read-only

Compare two versions of a document (PDF, DOCX, ODT, HTML, Markdown, or text) and get a diff of removed, added, and reworded paragraphs, with word-level changes and a symmetric similarity score.

Instructions

Compares two versions of a document — PDF, DOCX, ODT, HTML, Markdown or plain text — and returns which paragraphs were removed, added or reworded, with a word-level diff inside every reworded paragraph and a symmetric similarity score.

Kostenpflichtig: 0.002 USDC je Aufruf. Bezahlt per x402 auf Base, ohne Konto. Hoechstens 0.002 USDC je Aufruf.

Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworded, and for reworded blocks it names the individual words that went and came, so a single changed number in a long clause is visible instead of the whole clause being flagged. Alongside the content diff a structural comparison reports headings, paragraph, list and table-line counts on both sides. The similarity score is deliberately symmetric — two times the shared words divided by the sum of both lengths — because a one-sided measure would rate a heavily shortened document as almost unchanged. Both sides are measured the same way over the same units; if the two inputs arrive in different formats, so that one text comes out of a PDF and the other out of a DOCX, that is reported as a caveat, because part of any structural difference then comes from the extraction path and not from the documents. Ordering and duplicate paragraphs are handled by a shortest-edit-script diff, not by set comparison. What this endpoint does not do is judge: it says what changed, never whether the change is favourable, material or lawful. Preis 0.002 USDC je Aufruf, Abrechnung über x402.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
aYesThe earlier version. Exactly one of url, content_base64 or text.
bYesThe later version. Same shape as a.
ignore_caseNoCompare case-insensitively.
block_char_limitNoLonger block texts are shortened in the answer; the diff itself always runs on the full text.
ignore_whitespaceNoTreat runs of spaces and tabs as one space before comparing.
include_unchangedNoAlso list the unchanged blocks. Off by default — the changes are the answer.
max_blocks_returnedNoCeiling on returned blocks. What is dropped is counted and reported, never silently cut.
Behavior5/5

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

The description provides rich behavioral detail beyond the annotations: paragraph-level unit of comparison, word-level diffs for rewrites, symmetric similarity score formula, use of shortest-edit-script diff for ordering/duplicates, reporting of structural counts, and the caveat about different source formats. It also discloses the pricing model (0.002 USDC per call via x402), which is critical operational context. This far exceeds what readOnlyHint/openWorldHint/destructiveHint provide.

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 description is front-loaded with a strong first-sentence overview but becomes repetitive. The pricing information appears twice: once in German ('Kostenpflichtig: 0.002 USDC je Aufruf...') and again in English ('Preis 0.002 USDC je Aufruf, Abrechnung über x402.'). This redundancy inflates the length without adding value. Other sentences earn their place, but the duplicate pricing could be trimmed.

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?

Without an output schema, the description does an excellent job of explaining what the response will contain: lists of removed/added/reworded blocks, word-level changes within reworded blocks, structural counts, and a similarity score. It also covers algorithm choices, edge cases (different input formats), and limitations (no judgment). This is complete enough for an agent to invoke the tool and interpret results.

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?

The input schema already documents all 7 parameters with descriptions (100% coverage). The tool description adds no parameter-specific semantics beyond what the schema states: e.g., it doesn't elaborate on ignore_case or block_char_limit, but the schema's descriptions are clear. It does provide conceptual background (paragraph vs block) that indirectly helps understand parameters, but no direct enhancement. Baseline of 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?

The description opens with a precise statement: 'Compares two versions of a document — PDF, DOCX, ODT, HTML, Markdown or plain text — and returns which paragraphs were removed, added or reworded, with a word-level diff inside every reworded paragraph and a symmetric similarity score.' This names the resource (documents), the operation (compare), and the output format, clearly distinguishing it from sibling tools like cve_check or license_check.

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?

The description explains what the tool is for and what it explicitly does NOT do: 'What this endpoint does not do is judge: it says what changed, never whether the change is favourable, material or lawful.' It also warns about the caveat when inputs come from different formats. While it doesn't name alternatives, the purpose is so specific and the sibling tools are so different that usage context is sufficiently clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/halowerk/halowerk-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server