Skip to main content
Glama

RegAI Legal MCP (Taiwan)

search_domain_corpus

Read-onlyIdempotent

Search Taiwan's agency regulation databases (專業法規資料庫), ranked by relevance: 金融法規 (domain finance, 金融監督管理委員會 FSC) and 經濟法規 (domain economy, 經濟部 MOEA and its agencies -- 公司、商業登記、能源、水利、標準檢驗、貿易、產業、礦業、中小企業 etc.). Records: 法律, 法規命令, 實質法規, 行政規則, 函釋 (official interpretations), 公告, and for 經濟法規 also 司法判解 (court rulings the MOEA lists under the articles they apply; old 判例 carry a note on 法院組織法第57條之1). A law that is also in the main laws DB appears as a 綜合法規 article hit -- fetch it with get_article_by_number / get_law_details. Each record shows its 法規類別, issuer, 字號, date and -- when not plainly in force -- its status. Records no longer in force are excluded unless include_repealed. Omit domain to search all. Use get_domain_document for the full text. Requires MCP Pro or RegAI Pro.

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": {
      "query": "<query>"
    },
    "name": "search_domain_corpus"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitNoOnly records of this issuing unit: 金融法規 e.g. 銀行局, 證券期貨局, 保險局, 檢查局, 本會; 經濟法規 the MOEA unit's full name, e.g. 經濟部商業發展署, 經濟部水利署, 經濟部標準檢驗局, 經濟部能源署.
limitNoMax records (default 10, max 20).
queryYesQuestion or keywords in Traditional Chinese, e.g. "境外結構型商品可否以人民幣計價"; a 字號 such as "金管銀法字第11101445721號令" finds that record directly.
domainNoOnly these domains: finance 金融法規 (金融監督管理委員會), economy 經濟法規 (經濟部). Omit to search every domain.
law_classNoOnly these 法規類別: statute 法律, regulation 法規命令, substantive_rule 實質法規, admin_rule 行政規則, interpretation 函釋, notice 公告, judicial 司法判解 (經濟法規), other 其他. Omit for all.
include_repealedNoInclude records no longer in force (已停止適用). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / domain
      Added value: +{
      +  "description": "Only these domains: finance 金融法規 (金融監督管理委員會), economy 經濟法規 (經濟部). Omit to search every domain.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
    • changedInput schema / properties / law_class / description
      Previous value: -"Only these 法規類別: statute 法律, regulation 法規命令, substantive_rule 實質法規, admin_rule 行政規則, interpretation 函釋, notice 公告, other 其他. Omit for all."New value: +"Only these 法規類別: statute 法律, regulation 法規命令, substantive_rule 實質法規, admin_rule 行政規則, interpretation 函釋, notice 公告, judicial 司法判解 (經濟法規), other 其他. Omit for all."
    • changedInput schema / properties / unit / description
      Previous value: -"Only records of this issuing unit, e.g. 銀行局, 證券期貨局, 保險局, 檢查局, 本會."New value: +"Only records of this issuing unit: 金融法規 e.g. 銀行局, 證券期貨局, 保險局, 檢查局, 本會; 經濟法規 the MOEA unit's full name, e.g. 經濟部商業發展署, 經濟部水利署, 經濟部標準檢驗局, 經濟部能源署."
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: relevance-ranked results, repeal exclusion unless include_repealed, per-record status display when not plainly in force, and a plan requirement (MCP Pro / RegAI Pro). It does not discuss result ordering ties or pagination 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?

Front-loads the resource and its two domains, then layers record types and behavior; every clause carries information. It is dense and long for one paragraph, with some duplication of schema-stated defaults (include_repealed, omit-domain), which keeps it from a 5.

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 6-parameter, 100%-covered schema with no output schema, the description explains what each record displays (法規類別, issuer, 字號, date, status) and how repeal filtering works, which compensates for the absent output schema. Minor gaps remain around result ordering and paging, but an agent has enough to invoke it correctly.

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%, so the schema already documents unit, domain, law_class, limit and include_repealed, including 'Omit to search every domain' and the default-false repeal flag. The description's equivalent statements largely restate that, adding only the gloss that a 字號-style query finds a record directly.

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 Taiwan's agency regulation databases'), enumerates the two corpora (金融法規/FSC, 經濟法規/MOEA) and the record types indexed (法律, 法規命令, 函釋, 公告, 司法判解). It also distinguishes itself from the main laws DB by explaining how a law that also lives there surfaces as a 綜合法規 article hit.

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 concrete routing: use get_domain_document for full text, and get_article_by_number / get_law_details for laws mirrored from the main laws DB. It also says omitting domain searches every domain. It stops short of stating when an agent should prefer this corpus over search_law, leaving that inference to the agent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.