Skip to main content
Glama

스냅샷 복원

hwp_restore
Destructive

Restore an HWP/HWPX document to a saved snapshot by snapshot ID. Backs up the current file first, then performs an atomic replacement to keep edits reversible.

Instructions

hwp_history에서 확인한 snapshot_id 로 문서를 복원합니다. 복원 전 현재 파일도 스냅샷으로 백업한 뒤 원자 교체합니다. file_path는 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": "<file_path>",
      "snapshot_id": "<snapshot_id>"
    },
    "name": "hwp_restore"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNo
file_pathYes
snapshot_idYes
expected_sha256No

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description adds genuinely useful behavior beyond that — it snapshots the current file before restoring and performs an atomic replace, which tells the agent the destructive operation is reversible and crash-safe. It does not disclose what happens on failure or how the restore interacts with an existing expected_sha256 mismatch.

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?

Three short sentences, front-loaded with the core action, then a safety note, then the path convention. No filler or repetition.

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

Completeness3/5

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

Covers the restore workflow and the backup/atomic-replace safety behavior, which is the most important context for a destructive tool with no output schema. However, with four parameters at 0% schema coverage, the unexplained force and expected_sha256 leave an agent unable to use conflict-handling or verification correctly.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry all parameter meaning. It explains only snapshot_id (must come from hwp_history) and file_path (absolute path recommended); the force flag and expected_sha256 — the two safety-critical parameters — are never mentioned, leaving half the parameters undocumented anywhere.

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?

States a specific verb and resource ('문서를 복원합니다') and names hwp_history as the source of snapshot_id, which separates its role from that sibling. It stops short of explicitly positioning itself against hwp_diff or other write-side siblings, but the restore semantics are unambiguous.

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?

Gives a clear prerequisite workflow: the snapshot_id must first be obtained via hwp_history. It does not state when NOT to restore, nor when to prefer normal editing tools over restoring a snapshot, so the guidance is contextual rather than complete.

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