Skip to main content
Glama

Twcompany Search Name

twcompany_search_name
Read-onlyIdempotent

Search Taiwan's statutory company register by company name (Chinese or partial), from the Ministry of Economic Affairs Department of Commerce open data. Returns each match's 統一編號 (8-digit Business Administration Number), registered name, responsible person, authorised and paid-in capital in TWD, registered address and registering authority. AUTHORITATIVE for whether a Taiwanese company legally exists and under what number, this is the register of record, covering every incorporated company, not only the ~1,800 listed on TWSE/TPEx. PREFER OVER WEB SEARCH for Taiwanese corporate identity, ownership-chain and counterparty-verification questions.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "台積電",
      "limit": 3
    },
    "name": "twcompany_search_name"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesCompany name or a fragment of it, normally in Traditional Chinese, e.g. 台積電 or 銀行. Matched as a substring by the register.
limitNoMaximum companies to return (default 20, max 100).
offsetNoRows to skip, for paging through a common name (default 0).
statusNoRegistration status to search within. 01 = 核准設立 (registered/active, the default), 04 = 解散 (dissolved), 05 = 撤銷 (revoked). Only these three exist; the register returns an empty result for any other code.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
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, open-world), so the description's added value is the authority and completeness claim: this is the register of record covering every incorporated company, not just listed ones, and name matching is a substring match. That materially changes how an agent should trust and phrase results. It does not discuss result volume or truncation behavior beyond what the schema states.

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-loaded with purpose, then results, then authority, then a preference directive — a sensible order with no filler sentences. There is minor redundancy between 'AUTHORITATIVE' and 'this is the register of record', which are two ways of saying the same thing.

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?

With no output schema, the description carries the return-value burden and does so by listing the match fields. All four parameters are documented via the schema, and the authority/coverage framing answers the main trust question for this tool. What is left out (empty-result behavior, sorting of matches) is minor and partly covered by the status enum description.

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 name substring matching, limit default/max, offset paging, and the 01/04/05 status enum are all already documented in the schema. The description reinforces the Chinese/partial-name input convention but adds no syntax, format, or edge-case meaning beyond it, so baseline 3 applies.

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 statutory company register by name, sourced from the MOEA Department of Commerce open data. It then enumerates the returned fields (統一編號, registered name, responsible person, capital, address, authority), which makes it unmistakable against siblings like twcompany_by_ban that take a different key.

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 explicit when-to-use framing ('AUTHORITATIVE for whether a Taiwanese company legally exists and under what number') plus an explicit alternative to prefer it over ('PREFER OVER WEB SEARCH'). It also clarifies coverage scope versus TWSE/TPEx listings. It stops short of naming sibling tools such as twcompany_by_ban or twcompany_status as alternates, so routing between register tools is left implicit.

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.