check_dual_usePublic: cross-reference an HS code against the EU 2021/821 dual-use control list (and equivalents). Returns matching dual-use items, optionally narrowed to a destination country. A non-empty result means the product may need an export licence — surface it before signing a CartMandate.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | ||
| hs_code | Yes | HS code from lookup_hs_code. | |
| destination | No | Destination country (ISO-2). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that the operation is a lookup, that results can be narrowed by destination, and that non-empty results imply a potential export licence need. However, it does not mention empty-result behavior, side effects, or authorization, though 'Public:' hints at open access.
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 two tight sentences with no filler. The core purpose and the practical business consequence are both front-loaded, and every clause adds value.
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 read-only lookup with no output schema, the description covers the input, optional narrowing, and the meaning of a non-empty result. It does not explicitly state what an empty result means or how locale affects the response, but the core call decision is sufficiently supported.
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 67%, with hs_code described as coming from lookup_hs_code and destination described as ISO-2. The description adds the meaning of destination narrowing and the practical implication of results. Locale, however, has only an enum and no explanatory description in either the schema or the tool description, so the agent is left to infer its purpose.
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 opens with a specific verb and resource: 'cross-reference an HS code against the EU 2021/821 dual-use control list'. This clearly distinguishes it from siblings like check_sanctions and lookup_hs_code. The title reinforces the purpose, and the description leaves no doubt about what is checked.
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 concrete usage context: 'surface it before signing a CartMandate' and explains what a non-empty result means. It does not explicitly name alternatives or when not to use this tool versus check_sanctions, but the practical trigger is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool maps to a distinct resource and action: product/manufacturer retrieval, catalog search, category listing, HS classification, dual-use screening, sanctions screening, and partnership inquiry. The compliance checks are related but clearly separated by HS-code vs. name-based screening, so an agent is unlikely to pick the wrong tool.
Most tools follow a predictable verb_noun snake_case pattern: check_, get_, list_, search_, lookup_. partnership_inquiry is the only clear deviation, using a noun phrase instead of a verb-led name, but the overall convention is still easy to infer.
Nine tools is a well-scoped size for a public B2B trade and compliance server. Each tool covers a distinct step in the catalog-discovery or pre-flight workflow, with no redundant or decorative entries.
The core workflows are covered: category browsing, product search, manufacturer retrieval, HS classification, dual-use and sanctions screening, and partnership outreach. A minor gap is the lack of direct manufacturer text/country search, which is explicitly deferred to separate Wave 3b auth tools; agents can still discover manufacturers indirectly through product search.