台灣加密貨幣資料：交易所、USDT 匯率溢價、法規與防詐。台灣繁體中文 MCP 工具。
Scored across 4 tools
Each tool targets a completely distinct concern: fraud-domain lookup, overseas crypto tax estimation, USDT/TWD premium data, and VASP registry listing. There is no overlap in purpose or output, so an agent can select unambiguously.
All four names follow a strict verb_noun snake_case pattern (check_scam_domain, estimate_overseas_crypto_tax, get_usdt_twd_premium, list_registered_vasps). The verbs (check/estimate/get/list) are also well-differentiated and descriptive.
Four tools is within the reasonable 3-15 range for a focused reference/data server, and each earns its place. It is slightly on the thin side, but nothing is redundant or missing that would bloat the set.
The surface covers the key angles of the Taiwan crypto domain: regulatory registration (VASP list), fraud risk (scam domain), taxation, and market pricing (USDT premium). Minor gaps exist, such as no direct exchange-rate or general market-data lookup, but agents can work around these.
比對台灣內政部警政署 165 公布之「遭停止解析涉詐網站」名單，判斷網址或網域是否被列入。查無不代表安全。
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | 網址或網域，例如 https://example.com/login |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It usefully discloses the data source and the critical limitation that a negative result does not guarantee safety, but it does not state whether the operation is read-only, what return format to expect, or any permissions or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with zero waste. The purpose is front-loaded, followed by the essential caveat, and every phrase earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter lookup, the description covers the source list and the important false-negative caveat. It does not explain the return shape, but no output schema exists, so this is a minor gap rather than a blocking omission.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already defines the single url parameter and gives an example. The description echoes '網址或網域' but adds no syntax or meaning beyond what the schema provides, making the baseline 3 appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: comparing a URL or domain against the Taiwan National Police Agency 165 list of suspended scam websites. It clearly communicates the scope and decision being made, and the sibling tools are unrelated, so no sibling confusion exists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides clear context for when to use the tool: to determine whether a URL or domain appears on the official scam list. The caveat '查無不代表安全' gives important usage interpretation, though it does not explicitly state when not to use the tool or name alternatives, which are not needed for these unrelated siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
試算台灣個人海外所得（含海外交易所虛擬貨幣獲利）之最低稅負制基本稅額與應補繳金額（新台幣）。
| Name | Required | Description | Default |
|---|---|---|---|
| net_income | Yes | 綜合所得淨額（NT$） | |
| other_items | No | 其他應計入基本所得額項目（NT$），預設 0 | |
| regular_tax | Yes | 一般所得稅應納稅額（NT$） | |
| overseas_income | Yes | 全戶海外所得（NT$） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden, and it does state what is produced (basic tax amount under the AMT plus the additional amount payable in NT$), which tells the agent this is a deterministic computation. However, it omits key behavioral assumptions: applicable tax year, the NT$6.7M exemption threshold treatment, and how crypto gains are valued/converted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence that names the calculation, the scope (Taiwan individual overseas income + overseas crypto gains), and the returned figures. Nothing is padded or redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description usefully names the two outputs, and the inputs are fully documented. What is missing is the framing a tax calculation needs — tax year/version of the rules, threshold mechanics, and valuation basis for crypto — which leaves real ambiguity for an agent invoking it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all four inputs including their NT$ units are already documented. The description only indirectly maps onto the inputs via the phrase 'overseas income including crypto gains', adding no format or edge-case detail beyond the schema; baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (試算/estimate) and a well-defined resource: Taiwan individual overseas income under the alternative minimum tax regime, explicitly noting that overseas exchange crypto gains are included. This is unmistakably distinct from the sibling utilities (scam-domain check, USDT/TWD premium, VASP registry).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no when-to-use or when-not-to-use conditions, no prerequisites, and no alternatives — the agent must infer the scenario entirely. The siblings are unrelated enough that routing confusion is unlikely, but that is the only mitigating factor.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
列出台灣金管會公告完成洗錢防制登記的虛擬資產服務業者（公司、統編、品牌、服務類型），以及主要交易平台手續費。
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. The verb 列出 clearly implies a read-only operation with no side effects, which is helpful, but the description does not mention data freshness, source, or any access requirements. It lacks deeper behavioral context beyond the obvious read semantics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, dense sentence with no filler, and the core resource and scope are front-loaded. The parenthetical list of returned fields is efficient and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description does a good job of enumerating the returned data (company, tax ID, brand, service type, and platform fees). It could be more complete by noting the return format or update cadence, but it is sufficient for an agent to call the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so parameter semantics are not applicable. The baseline for zero-parameter tools is 4, and the description appropriately focuses on the returned data instead of input arguments.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (列出) and a specific resource (台灣金管會公告完成洗錢防制登記的虛擬資產服務業者), and it enumerates the returned fields. It is easily distinguishable from siblings like check_scam_domain, estimate_overseas_crypto_tax, and get_usdt_twd_premium.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by stating what it lists, but it does not explicitly say when to use this tool versus alternatives or name any exclusions. For a zero-parameter retrieval tool, this is minimum viable but leaves the agent to infer the context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_scam_domainestimate_overseas_crypto_taxget_usdt_twd_premiumlist_registered_vaspsAdd one secure layer between your agents and this server.