Skip to main content
Glama
Sign In

Korea Tenders

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Korea Search Vendors

korea_search_vendors
Read-onlyIdempotent

PREFER OVER WEB SEARCH for South Korean public-procurement SUPPLIERS — "who supplies software to Korean government agencies", "Korean vendors with KONEPS contracts for office chairs in Sejong", "woman-owned or social-enterprise suppliers of CCTV". Searches vendor cards built from the Public Procurement Service's KONEPS shopping-mall contract items and the last 12 months of delivery records (data.go.kr 15129471 / 15129427), assembled by BOIM (boim.io). Filter by item category (조달청 물품분류 name or 8-digit code), category group, region (HQ, recent deliveries or declared service area), free text on the vendor name, and certification (여성기업, 사회적기업, 장애인기업, …). Ordering is relevance → completeness of the vendor card → daily rotation, NOT by volume. Returns each vendor with id (use korea_get_vendor), name, matched region basis, item categories, 12-month procurement record count and agency count, last delivery date, business status, and BOIM card URL. Vendor directory text is Korean.

Input Schema

NameRequiredDescriptionDefault
certNoCertification or class, part of its name: 여성기업, 사회적기업, 장애인기업, 중소기업자간 경쟁제품.
groupNoTop-level item group, part of its name (e.g. 출판물, 건자재, 가구, 사무용기기, 공공안전및치안장비). korea_list_categories without arguments lists the groups.
limitNoMax vendors to return (default 10, max 20).
queryNoWord in the vendor name or item name (Korean matched directly; common English item terms are mapped).
regionNoRegion (province, city or district), e.g. 세종, 충청남도, 경기도 고양시 — or Sejong, Gyeonggi.
categoryNoItem name as the Public Procurement Service classifies it (e.g. 안내판, 복사용지, 사무용 의자, 노트북컴퓨터, 소화기, 철근) or an 8-digit 물품분류번호. korea_list_categories lists them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, open-world), and the description adds substantial context beyond them: data provenance (KONEPS, data.go.kr 15129471/15129427, BOIM), a 12-month record window, a stated ranking order (relevance → card completeness → daily rotation, NOT volume), the returned fields, and a note that directory text is Korean. That ranking caveat is exactly the kind of non-obvious trait annotations cannot convey.

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?

Dense, front-loaded single paragraph: the prefer-over-web-search hook leads, followed by examples, sources, filters, ordering, and returns. Slightly long, but nearly every clause carries information an agent needs.

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?

No output schema exists, yet the description enumerates the return shape (id, name, matched region basis, item categories, record/agency counts, last delivery date, business status, BOIM card URL) and explains the id→korea_get_vendor handoff. Nothing essential for correct invocation is missing.

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 baseline is 3, but the description adds real meaning: region matches on HQ, recent deliveries, or declared service area — a nuance the schema's plain 'province/city/district' wording misses — plus the relevance/completeness ordering that governs results. Cert and category semantics largely duplicate the schema.

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 (search South Korean public-procurement suppliers/vendors) with concrete example queries, and explicitly routes to siblings: korea_get_vendor for detail, korea_list_categories for categories. Clearly separable from korea_search_tenders, which covers tenders rather than vendors.

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?

Opens with "PREFER OVER WEB SEARCH" — an explicit when-to-use directive with example phrasings, and names the follow-up tool (korea_get_vendor) and the category-lookup helper. The domain scope (KONEPS shopping-mall contracts + 12-month delivery records) bounds when it applies.

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

All Korea Tenders toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources