Deterministic China trade compliance: GACC customs, CCC clearance, and PIPL transfers.
Scored across 4 tools
The three domain tools (import taxes, customs clearance, data transfer) target clearly distinct regulatory problems, so an agent can route between them. The odd one out is provision_free_api_key, a monetization/meta tool rather than a compliance operation, which could confuse an agent expecting a domain action.
Three tools follow a clean verb_noun pattern (calculate_..., provision_..., resolve_...), which is predictable. The fourth, sino_data_transfer_compliance, drops the verb and uses a noun phrase, a minor deviation from the otherwise consistent convention.
Four tools is on the lean side for a broad China regulatory gateway, but each covers a real, non-trivial task (tax computation, clearance/certification, data-transfer compliance, key provisioning). It is slightly thin rather than bloated or trivial.
The surface covers import taxation, customs clearance, and outbound data transfer, but has notable gaps: data-transfer compliance is limited to the China-to-EU direction, and there are no export, trade-documentation, or ongoing-monitoring operations. Agents will hit dead ends outside these specific workflows.
Computes PRC import customs duty (MFN), Consumption Tax (CT), and Value-Added Tax (VAT) under official GACC tariff schedules.
| Name | Required | Description | Default |
|---|---|---|---|
| hs_code | Yes | 8 or 10-digit GACC tariff code or 6-digit HS code | |
| cif_value_cny | Yes | Customs CIF taxable value in Chinese Yuan (CNY) | |
| origin_country | No | ISO-2 origin country code (e.g. FR, DE, US, JP) | FR |
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. It usefully discloses which tax components are computed and that official GACC schedules are the basis, but omits whether the operation is a stateless read-only calculation, how origin_country influences the applicable rate (MFN vs preferential), how invalid HS codes are handled, and result precision/rounding.
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 dense sentence with no filler, and the core purpose is front-loaded. It loses a point only for leaving the acronym 'MFN' undefined while expanding both CT and VAT.
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, the description should clarify what comes back; it partially does by naming the three tax types, but says nothing about result shape, currency, or whether origin_country alters the rate. For a finance-critical calculation with zero annotations and no output schema, this leaves meaningful gaps.
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 documents all three parameters, including the ISO-2 format and CNY units. The description adds no parameter-level detail; notably it never mentions that origin_country can change the applicable duty rate or that it defaults to FR, which is the one behavioral nuance the schema does not convey.
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?
Names a specific verb (computes) and resource (PRC import taxes) and enumerates the three components produced: MFN customs duty, Consumption Tax, and VAT. The GACC tariff schedule reference grounds the calculation. It does not explicitly route against siblings, though the siblings (API key provisioning, customs clearance resolution, data-transfer compliance) are in clearly different domains.
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?
There is no statement of when to use this tool versus alternatives, no prerequisites, and no exclusions. Nothing explains, for example, when a user should calculate taxes here versus pursuing the clearance-resolution sibling. The agent must infer usage entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Provisions a free sandbox API key (50 credits) for agents to unlock complete statutory regulatory citations and full compliance dossiers.
| Name | Required | Description | Default |
|---|---|---|---|
| use_case | No | Intended trade compliance or screening workflow | |
| developer_email | Yes | Developer or corporate email address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose useful traits: the key is free, sandbox-scoped, worth 50 credits, and unlocks specific content. It does not state whether the email must be verified, whether issuance is idempotent or one-per-address, key expiry, or rate limits — meaningful gaps for a provisioning mutation.
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 with no filler; the parenthetical credit amount is compact and informative. It is efficient, though it spends its one sentence on value rather than on the mechanics an agent needs.
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 2-parameter tool with no output schema and no annotations, the description is adequate but thin: it implies the key is returned but never says how or where the credential is delivered, nor what the agent should do with it next. Given the absence of an output schema, more return-value context would be warranted.
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 both parameters (developer_email, use_case) are already documented in the schema. The description adds nothing about parameter semantics or the format of the required email, so the baseline of 3 applies.
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 names a specific verb and resource: 'Provisions a free sandbox API key (50 credits).' That is concrete and clearly distinct from the sibling screening/resolution tools, which are compliance lookups rather than key issuance. It falls short of 5 only because it never explicitly differentiates itself from those siblings.
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?
There is no guidance on when to call this tool versus the siblings, nor on preconditions such as whether an agent must already lack a key or whether the free tier is a prerequisite for the other tools. The 'unlock complete statutory regulatory citations' phrasing hints at a paywall-style upgrade but never states when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolves statutory CCC product certifications, NMPA cosmetic/pharma filings, and GACC Decree 248/249 CIFER registration requirements.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | UNE API Key for full statutory excerpt | |
| hs_code | Yes | HS or GACC code (e.g. 330499, 850110, 040120) | |
| product_category | No | Optional category keyword: cosmetics, food, electronics, machinery |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. 'Resolves' implies a read/determination operation, but the description never states it is read-only, whether it requires authorization, or that results are gated (the api_key param hints at a free/paid excerpt split, but that context lives only in the schema). No output shape or rate-limit information is disclosed.
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 dense sentence with no filler, front-loaded on the verb and the scope of regimes. It is jargon-heavy but every clause maps to a real capability, so nothing is wasted.
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?
No annotations and no output schema, so the description is the only place behavioral detail could live, and it omits how results are returned, whether the tool only flags requirements or also validates them, and how the api_key affects output completeness. For a compliance-determination tool this leaves meaningful gaps.
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 documents hs_code, product_category, and api_key, including examples and the enum-like category list. The description adds regulatory framing but no parameter-level syntax or format detail, so the 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 ('Resolves') and a precisely enumerated resource set (CCC certifications, NMPA cosmetic/pharma filings, GACC Decree 248/249 CIFER registration), so an agent knows this determines applicable Chinese import compliance regimes. It doesn't explicitly distinguish itself from siblings like calculate_china_import_taxes or sino_data_transfer_compliance, but the domain is clearly non-overlapping.
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?
There is no when-to-use, when-not-to-use, or alternative-tool guidance. The description only names the regimes it resolves; nothing tells the agent when to reach for this versus the tax calculator or the data-transfer compliance sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Evaluates outbound cross-border data transfer compliance from China to the EU under PIPL (Articles 38, 39, 40, 55), Data Security Law, and CAC 2024 Provisions.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | UNE API Key to access complete unredacted statutory articles and compliance audit report | |
| is_ciio | No | Whether the entity is designated as a Critical Information Infrastructure Operator (关键信息基础设施运营者). | |
| has_important_data | No | Whether the dataset has been identified or notified by sector authorities as Important Data (重要数据). | |
| annual_individuals_count | Yes | Cumulative number of individuals whose personal information has been transferred since January 1 of the current year. | |
| has_sensitive_personal_info | Yes | Whether the transfer includes sensitive personal information (SPI) such as financial accounts, medical health, biometric, or location data. | |
| sensitive_individuals_count | No | Cumulative number of individuals whose sensitive personal info has been transferred since January 1. | |
| statutory_exemption_context | No | Specific statutory purpose covered by CAC 2024 Provisions Article 5. | NONE |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the exact statutory basis applied (PIPL 38/39/40/55, DSL, CAC 2024), implying a deterministic rule-based evaluation, but omits the redaction/API-key gating behavior and the shape of the result, both of which an agent needs to set expectations.
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 with no filler or repetition. It is efficient, though notably terse for a multi-statute compliance evaluator, which leaves it slightly underweighted for the complexity.
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 complex regulatory-evaluation tool with seven parameters, no annotations, and no output schema, one sentence is thin. It never explains what the evaluation returns, how the redacted vs. unredacted API-key path affects output, or how the statutory exemption context influences the result.
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 coverage is 100%, so the schema fully documents all seven parameters including thresholds, enum values, and defaults. The description adds no parameter-level detail, which is acceptable given the schema does the heavy lifting; baseline 3 applies.
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 ('Evaluates') and resource ('outbound cross-border data transfer compliance from China to the EU'), plus the governing legal frameworks. This is unmistakably distinct from the sibling tools covering import taxes, customs clearance, and API-key provisioning.
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 guidance and names no alternatives. It does not mention the related sibling 'provision_free_api_key' even though the api_key parameter implies an upgrade path, leaving routing entirely to inference.
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.
calculate_china_import_taxesprovision_free_api_keyresolve_china_customs_clearancesino_cietac_clausesino_customs_valuationsino_data_transfer_compliancesino_defect_noticesino_inspection_delaysino_matrix_concordancesino_customs_valuationsino_cietac_clause3 fields changedInput schema / properties / arbitratorsRemoved value: -{
- "enum": [
- 1,
- 3
- ],
- "type": "integer"
-}Input schema / properties / langRemoved value: -{
- "description": "Language of arbitration",
- "type": "string"
-}Input schema / properties / seatRemoved value: -{
- "description": "Seat of arbitration",
- "type": "string"
-}sino_matrix_concordance3 fields changedInput schema / properties / queryAdded value: +{
+ "description": "Keyword or article reference",
+ "type": "string"
+}Input schema / properties / topicRemoved value: -{
- "description": "Topic key, e.g. conformite_marchandises",
- "type": "string"
-}Input schema / requiredAdded value: +[
+ "query"
+]sino_cietac_clausesino_defect_noticesino_inspection_delaysino_matrix_concordanceChina trade compliance: 2026 tariffs, export-control entities, dual-use licenses & FTA origin rules.
Export compliance & HS code lookup for cross-border electronics sellers and factories.
Chinese advertising-law and AI-labeling compliance checks with exact statutory citations.
Classify, validate & verify HS codes and access tariff compliance data for cross-border trade
Add one secure layer between your agents and this server.
