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

Annotations already declare it a safe, idempotent, open-world read, so the description is free to spend its words on calculation semantics: NBU rate of the calculation day, shipping excluded from the base, and the EUR 10,000 ceiling where different rules take over. It leaves the actual returned breakdown unexplained, which costs it a point given there is no output schema.

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 dense but front-loaded sentences: trigger first, then scope, threshold, and the exclusion/alternative. The bilingual glosses add length but earn it by matching the user's language. Minor redundancy between the 'goods value only' phrase here and in the schema.

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 three-parameter read-only estimator with no output schema, the description covers audience, inputs, rate source, and the boundary where it stops applying. What is missing is any hint of the result shape (e.g., separate duty vs VAT lines) or the duty-free threshold logic, which an agent might want when explaining the estimate.

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 baseline is 3; the description nevertheless reinforces the non-obvious parts — goods value only, shipping excluded, EUR or USD invoice currency — and states the EUR 10,000 ceiling that the schema expresses only as a raw 10000000 maximum. It does not describe the date parameter's Kyiv-time default, but the schema does.

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 and resource ('estimate Ukrainian import duty and VAT for an individual's personal express parcel') and explicitly contrasts itself with check_customs for companies. The parenthetical Ukrainian synonyms (мито, ПДВ, розмитнення) make the intent unmistakable against all nine 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?

Opens with an explicit trigger ('Use when an individual asks how much duty/VAT they will pay'), gives a hard validity bound (EUR 10,000 goods value, above which business rules apply) and names the alternative for the excluded case (check_customs plus a broker). Both inclusion and exclusion conditions are covered.

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