ooxml-integrity

Overview Schema Source Related Servers Discussions Admin

Check an edited .docx against its original

compare

Read-onlyIdempotent

Checks an edited .docx or .pptx against the original to find lost comments, tracked changes, notes, headers/footers, and text, and to honor declared expected changes.

Instructions

Everything check does on the edited file, plus what the edit lost relative to the original: comments, tracked insertions and deletions, footnotes and endnotes, headers and footers, text. Same as ooxml-integrity check EDITED --against SOURCE --json --coverage. For a .pptx only the layout checks run and the comparison is reported as not performed (FID000). If the user asked for a change that removes something, such as accepting or rejecting a tracked change or rewriting a header untracked, declare it in expect: a matching finding is reported as expected instead of failing, and an expectation nothing matches fails with EXP001.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>",
      "edited": "<edited>"
    },
    "name": "compare"
  }
}

Input Schema

Name	Required	Description
`edited`	Yes	the edited copy; path on this machine; absolute, or relative to the server's working directory. URLs are rejected
`expect`	No	changes the edit was asked to make, as [[expect]] entries in docs/configuration.md, without path
`source`	Yes	the original document; path on this machine; absolute, or relative to the server's working directory. URLs are rejected
`introduced`	No	true reports only what the edit introduced: a finding the original already has, such as a comment an earlier tool orphaned, is listed as suppressed instead of failing. Lost content (FID) and anything not checked always count. Default false

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered; the description adds substantial behavior on top: format-dependent degradation for .pptx, expectation-suppression semantics, the EXP001 failure mode for unmatched expectations, and the suppression behavior implied by `introduced`. It does not describe the report structure an agent will receive from `--json --coverage`, which is the main remaining gap.

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?

Front-loaded with the core comparison statement before the edge cases, and every sentence carries information (coverage list, CLI equivalence, pptx limitation, expect semantics). The middle sentence quoting the CLI invocation is the least useful to an agent caller and 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?

For a read-only comparison tool with full schema coverage and no output schema, the description covers scope, format-specific behavior, the opt-in expectation mechanism with its error code, and the suppression flag — enough for an agent to call it correctly. No return-value documentation is required since no output schema is declared, though the `--json --coverage` phrasing assumes CLI knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds real semantic value for `expect`: why you declare it (a requested removal), that a matching finding is reported as expected rather than failing, and that an unmatched expectation fails with EXP001. That is meaning the schema alone does not convey.

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?

States a specific verb and resource — compares the edited file against the original — and enumerates exactly what is checked (comments, tracked changes, footnotes/endnotes, headers/footers, text). It also positions itself relative to the sibling `check` as a strict superset, so an agent can distinguish the two without opening either schema.

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?

Clear context for use: whenever an original exists and loss relative to it matters, plus the explicit caveat that .pptx only runs layout checks and reports comparison as not performed (FID000). It also tells the agent when to populate `expect` instead of letting a removal fail. It stops short of stating the inverse (use `check` when no original is available), leaving that to inference.

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

Deploy Server

Other Tools

checkA
compareA