Skip to main content
Glama
opendata-kr

@opendata-kr/narajangteo-bid-mcp

Official
by opendata-kr

입찰공고 첨부 다운로드·파일 목록

download_attachments

Download bid notice attachments to disk, extract ZIP archives, and return a file catalog. Refresh to re-download if attachments update.

Instructions

입찰공고 첨부를 전부 디스크에 내려받고 ZIP은 풀어(원본 ZIP은 지운다), 읽을 수 있는 파일 목록(카탈로그)만 반환한다(본문 텍스트는 담지 않는다). 각 파일 본문은 read_attachment에 이 목록의 index를 줘서 읽는다(불필요한 재조회 없이 필요한 파일만 읽는다). ZIP은 목록에서 사라지고 내부 파일이 공고 폴더에 평탄하게 풀려 항목으로 나오며 container에 원본 ZIP명이 담긴다. 첨부의 URL만 필요하면 get_bid_attachments를 쓴다. 저장 위치는 DATA_GO_KR_DOWNLOAD_DIR(미설정 시 ~/Downloads) 아래 공고번호 폴더다. 첨부가 나중에 바뀌면 refresh=true로 다시 호출한다. 각 항목의 extractable=true면 read_attachment로 본문(HWPX·구형 HWP·구형 DOC)을 읽을 수 있고, false면 파일만 저장돼 있어 savedPath로 직접 열어야 한다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
refreshNotrue면 디스크 캐시를 무시하고 모든 첨부를 새로 내려받아 카탈로그를 다시 만든다(첨부가 갱신됐을 때). 기본 false는 이미 받은 파일·카탈로그를 재사용한다.
bidNtceNoYes입찰공고번호. 이 공고의 전 첨부를 디스크에 내려받고 ZIP은 풀어(원본 ZIP은 삭제) 읽을 수 있는 파일 목록(카탈로그)을 반환한다. 개별 파일 본문은 read_attachment로 읽는다.
Behavior5/5

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

Thoroughly describes side effects: downloads, extracts ZIPs, deletes original ZIP, stores in specific directory, uses cache, and refresh behavior. Annotations (readOnlyHint: false, openWorldHint: true) are consistent with this mutation behavior.

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?

Information-dense paragraph that front-loads the main action. Could be slightly more structured (e.g., bullet points), but every sentence adds value and it's not overly long.

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?

With no output schema, the description fully explains the return (file catalog without text), how to use indices with read_attachment, directory location, cache behavior, and non-extractable files. Comprehensive for a 2-parameter tool.

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

Parameters5/5

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

Schema coverage is 100%, and the description adds significant context: explains refresh (ignore cache) and bidNtceNo (triggers download/extraction). Also details how results are used with other tools, adding value beyond schema descriptions.

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 clearly states the tool downloads all attachments, extracts ZIPs (deleting originals), and returns a file catalog. It distinguishes from siblings: get_bid_attachments for URLs only, read_attachment for reading file content.

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

Usage Guidelines5/5

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

Explicitly mentions when to use: when you need downloaded files and a catalog. Advises using get_bid_attachments for URLs only, and read_attachment with index for file content. Also explains refresh parameter for updated attachments.

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/opendata-kr/narajangteo-bid-mcp'

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