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

With annotations readOnlyHint=true and idempotentHint=true, the description adds substantial behavioral context: the exact tax calculation logic (using customs decadal exchange rates), the NT$2,000 small-amount exemption rules including exceptions (tobacco/alcohol, six-month frequency limit), exclusions (oversize fee), and a disclaimer that results are reference-only pending customs approval. It complements the annotations without contradiction.

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 paragraph but every sentence adds value. It's front-loaded with the core purpose, then systematic breakdown of taxes, input requirements, and exclusions. It could be split into bullets for easier scanning, but given the complexity, the length is justified and there is no redundancy.

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?

Given 15 parameters, an output schema, and a complex multi-tax calculation, the description is remarkably complete. It covers included taxes, exemption logic, exchange rate derivation, exclusions, a pointer to a sibling tool for oversize fees, and a disclaimer. The output schema handles return details, so the description's summary of return contents is sufficient.

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?

Although schema_description_coverage is 100%, the description adds critical relational meaning: it identifies currency_code and price_foreign as required, explains that volume_liters and alcohol_degree are needed for liquor tax and tobacco_sticks for tobacco tax, and clarifies that product_description enables AI classification when hs_code is absent. This goes beyond individual schema descriptions to explain how parameters interact in the calculation.

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 '試算進口台灣的法定稅費' (estimate legal import taxes to Taiwan), a specific verb+resource definition. It lists all tax components (import duty, business tax, commodity/liquor/tobacco tax, trade promotion fee) and explicitly distinguishes itself from sibling tools like lucky_ccc_tariff_lookup and lucky_hct_oversize_fee by stating its scope and pointing to the latter for oversize fees.

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 clearly states when to use the tool: for full tax estimation, and explicitly says the result excludes Taiwan local HCT oversize fees, directing users to lucky_hct_oversize_fee for large packages. It also explains when to provide hs_code vs product_description (AI auto-classification when hs_code missing), and notes required fields despite the schema marking them as optional. This provides strong when/when-not guidance.

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