antidumping_check

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description adds real value on top by specifying the returned fields (EEC decision, per-producer duty rates, expiry date, link). Crucially it discloses the dataset's bounded coverage — measures renewed in 2026 only, not exhaustive — which is exactly the kind of non-obvious behavior that prevents false negatives.

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?

Purpose is front-loaded in the first clause, followed by return contents and then the coverage caveat, so the agent gets what it needs early. The only waste is the awkward sentence break inside 'the decision that sets duty rates', which is a formatting artifact rather than redundant content.

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 correctly takes on the burden of describing return values (decision, rates, expiry, link), and the non-exhaustive caveat handles the main correctness risk. What is still missing is the filter-combination semantics for a tool whose three parameters are all optional, which matters for a lookup that may return everything.

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%, with each of the three parameters already documented including examples ('грузовые шины', 'CN, UA, AZ'), so the baseline is 3. The description restates the parameter names but does not explain how they combine (AND vs OR) or how prefix matching on the TN VED code behaves, so it adds little beyond the schema.

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 — 'Check EAEU trade defence measures (antidumping duties)' — plus the three facets it can be queried by (code, product, origin country). This is a distinct domain from siblings like tnved_search or classification_rulings_search, so an agent can route to it without ambiguity.

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?

Usage is only implied through the parameter list; the description never states when to prefer this over tnved_search or tnved_code_info, nor whether all three filters are optional (i.e. that an empty call lists everything). The one genuine guidance element is the caveat that absence of a match is not proof a measure applies, which tells the agent how to interpret a negative result.

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