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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real value: it declares the call is free and rate-limited, and it describes the response shape (duty lines, fees, per-unit conversion in cents, tax-date notes). It stops short of stating whether results are cached, how tax dates affect validity, or what rate limits actually are.

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 English text is front-loaded and efficient, leading with the action and then the I/O contract. However, the entire passage is duplicated in Chinese verbatim, doubling length without adding new information for an agent, which weakens density. Structure is fine; the redundancy costs it.

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?

It compensates for the missing output schema by describing the return payload, which is the biggest completeness win. But with 7 parameters, 0% schema coverage, and no annotations describing semantics, an agent still cannot confidently supply origin, mode, or freight_usd, and the meaning of 'tax-date notes' is left opaque.

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 0% for 7 parameters, so the description carries the full burden and only partially discharges it. It names hts_code, product, fob_usd and quantity, but says nothing about mode, origin, or freight_usd — and origin and freight are materially important for a landed-cost calculation. Three undocumented parameters with zero schema help is a substantial gap.

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 (estimate) and resource (landed cost) and spells out both the inputs it consumes (hts_code or product, fob_usd, quantity) and the outputs it produces (duty lines, fees, total/per-unit cents, tax-date notes). That is far beyond a restated title. It does not name or distinguish itself from any sibling, though no sibling in the list appears to be a competing cost estimator, so the practical ambiguity is low.

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 'hts_code or product' phrasing implies the two entry paths, and 'free, rate-limited' hints at how freely to call it. But there is no statement of when to prefer this over other steps in the order/compliance workflow, and no exclusion of cases where it would be inappropriate (e.g. quoting vs. estimating). Usage must be inferred from the workflow context.

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