Skip to main content
Glama
Sign In
tw-mcp

tw-mcp

by Larryveryhandsome
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

實價登錄查詢

lvr_search
Read-onlyIdempotent

Search Taiwan real estate actual transaction prices by district, type, date, and price range to get median and quartile unit price statistics and deal details.

Instructions

查實價登錄成交行情：篩選地區、型態、期間、價格，預設排除特殊交易，回傳單價中位數／四分位數、各區統計與成交明細。 資料用內政部開放資料（使用者自行下載的 CSV／ZIP）；沒給檔案時是虛構示範資料，回覆時要講明。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "lvr_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo回傳幾筆明細
orderNo排序方向desc
countyNo只讀 ZIP 裡某個縣市，例如 臺北市、高雄市
age_maxNo屋齡上限（年）
age_minNo屋齡下限（年）
date_toNo交易日迄，2025-12-31 或民國 1141231
keywordNo地址／備註關鍵字，例如路名、社區附近路段
sort_byNo排序欄位date
area_maxNo建坪上限
area_minNo建坪下限
csv_pathNo內政部實價登錄開放資料的 .csv（*_lvr_land_a.csv 不動產買賣）或整包 .zip 的本機路徑；留空＝用內建虛構示範資料
unit_maxNo單價上限（萬元/坪）
unit_minNo單價下限（萬元/坪）
date_fromNo交易日起，2024-01-01 或民國 1130101
districtsNo鄉鎮市區，例如 ['大安區','信義區']
price_maxNo總價上限（萬元）
price_minNo總價下限（萬元）
building_typesNo建物型態
buildings_onlyNo只算有建物的交易（排除純土地、純車位）
include_specialNo是否包含親友、員工、特殊關係、瑕疵、凶宅、法拍等特殊交易（預設排除，不適合比價）

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the data-provenance behavior: it runs on Ministry of Interior open-data CSV/ZIP files supplied by the user, and silently falls back to fictional demo data when none is given — with a hard requirement to say so in the reply. That is a non-obvious trait an agent must know, though the description does not discuss pagination, performance on large ZIPs, or error behavior for bad paths.

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 sentences, both front-loaded and dense: the first states capability and output, the second states data provenance and the mandatory disclosure caveat. Nothing is wasted and no sentence merely repeats the name or the schema.

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 20-parameter, no-output-schema tool, the description does the work the missing output schema would have done by naming the return contents (median/quartiles, per-district stats, transaction rows) and explains the data source and demo-data caveat. The main residual gap is that it does not describe behavior when csv_path is invalid or when filters match nothing.

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 100% across all 20 parameters, including units (萬元/坪), date formats (民國 vs ISO) and enum values, so the schema carries the parameter burden. The description only restates the filter categories and the default exclusion of special transactions, adding no syntax or edge-case detail beyond the schema — baseline 3.

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 names a specific verb and resource (查實價登錄成交行情) and enumerates the filter axes (地區、型態、期間、價格) plus the return shape (單價中位數／四分位數、各區統計、成交明細). An agent can tell exactly what this tool produces without opening the schema. The sibling tools (about, pdf_pages, pii_mask, tw_workdays) are unrelated utilities, so no sibling disambiguation is needed.

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 context is implied rather than stated: the description notes that special transactions are excluded by default (不適合比價 is only in the schema), and that the caller must disclose when demo data is being used. There is no explicit when-to-use / when-not-to-use guidance or named alternative, which is acceptable given no comparable sibling exists, but the guidance is still only implicit.

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

Deploy Server

Other Tools