Skip to main content
Glama

문서 텍스트 비교

hwp_diff
Read-only

Compare HWP/HWPX documents or a current file against a saved snapshot to return a unified text diff, helping identify changes between versions.

Instructions

두 문서 파일(file_path_a vs file_path_b) 또는 현재 문서와 스냅샷(snapshot_id) 간의 텍스트 unified diff 를 반환합니다. file_path_a는 절대 경로 권장.

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": {
      "file_path_a": "<file_path_a>"
    },
    "name": "hwp_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
passwordNo
file_path_aYes
file_path_bNo
snapshot_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that the output is a unified diff (a useful return-format hint for a tool with no output schema) and that file_path_a should be an absolute path, but it says nothing about behavior when neither file_path_b nor snapshot_id is supplied, nor about error conditions on missing files.

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?

Two short sentences, front-loaded with the core action and both modes, with the absolute-path note trailing. Nothing is padded and no sentence repeats the tool name or schema text verbatim.

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 read-only diff tool with no output schema, the description covers the essential calling modes and the return format. The remaining gaps — the undocumented password parameter and the absence of mutual-exclusivity rules between file_path_b and snapshot_id — are modest but real for a 4-parameter tool at 0% schema coverage.

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 0%, so the description carries the burden. It successfully explains the relationship among file_path_a, file_path_b, and snapshot_id and adds a path-format recommendation, but the password parameter is never mentioned and it never states that only file_path_a is required while the others are alternative options.

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 states a specific verb and resource ('텍스트 unified diff 를 반환합니다') and names both operating modes: two files (file_path_a vs file_path_b) or current document vs snapshot (snapshot_id). It does not distinguish itself from text-extraction siblings such as hwp_get_text, so an agent must infer that this tool computes a comparison rather than a plain read.

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

Usage Guidelines3/5

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

Usage is implied by naming the parameter pairings — the agent can tell that file_path_a+file_path_b and file_path_a+snapshot_id are the two valid configurations. There is no explicit when-not-to-use guidance or pointer to alternatives like hwp_get_text or hwp_history for non-diff reads.

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