Skip to main content
Glama

표 셀 채우기

hwp_fill_cells
Destructive

Fills HWP/HWPX table cells in bulk by row/column coordinates or label-based targeting, with safe writes, backups, loss verification, and atomic replacement.

Instructions

표의 셀 값을 일괄 채웁니다. 각 항목은 좌표 기준({'row': 0, 'col': 1, 'text': '값'}) 또는 라벨 기준({'label': '성명', 'text': '홍길동', 'direction': 'right'|'below'})을 지원합니다. 라벨 기준에서 표 번호('table' 또는 table_index)를 생략하면 모든 표를 앞에서부터 찾아 첫 일치를 씁니다. 좌표 기준에서 표 번호를 생략하면 0번 표입니다. SafeWriter를 통해 스냅샷 백업 및 무손실 검증 후 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>",
      "cells": "<cells>"
    },
    "name": "hwp_fill_cells"
  }
}

Input Schema

NameRequiredDescriptionDefault
cellsYes
forceNo
passwordNo
file_pathYes
allow_lossNo
table_indexNo
expected_sha256No

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds substantive behavior beyond that: a SafeWriter path with snapshot backup, lossless verification, and atomic replacement, plus a recommendation to use absolute file_path. It does not explain what force, allow_loss, or password do in that pipeline, but the core write semantics are well disclosed.

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?

The description is front-loaded with the two addressing modes before the safety mechanics, and each sentence carries information. It is dense but not padded; the only minor inefficiency is that the table-number rules are stated twice (once per mode).

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?

For a destructive, 7-parameter mutation tool with no output schema and zero schema-level descriptions, the definition is reasonably complete on cell addressing and write safety. It falls short on password/encryption handling and on allow_loss/force/expected_sha256, which an agent needs to decide whether a lossy overwrite is acceptable.

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% across 7 top-level parameters, so the description carries the burden and does explain the nested cells contract (row/col/text, label/text/direction, and the table vs. table_index omission defaults). But force, password, allow_loss, expected_sha256, keep_style, and occurrence are never mentioned, and these are exactly the parameters that govern the lossy-write escape hatch it advertises.

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 opens with a specific verb and resource ('표의 셀 값을 일괄 채웁니다' – bulk-fill table cell values), so an agent immediately knows it mutates table cells rather than body text or form fields. It does not name sibling tools such as hwp_fill_fields or hwp_insert_text, so differentiation from alternatives is left to inference.

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?

The description gives clear operational routing between the two supported addressing modes (coordinate vs. label) and states the default table-selection behavior for each, which is genuinely useful when-to-use logic. However, it never says when to prefer this tool over hwp_fill_fields or hwp_insert_text, and gives no exclusions or prerequisites such as document type or encryption state.

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