Gateway Lines Tariff

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value beyond that by disclosing the return shape (multiple candidate codes with descriptions and base duty rates) and that the call is not billed, which matters for planning.

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?

Three short sentences, front-loaded with what it does, then the return value, then the routing rule and billing note. No filler and no repetition of the title.

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?

An output schema exists so return values need only be summarized, and the description does that. For a one-parameter read-only lookup this is nearly complete; it could add a hint about how specific the product description should be, which matters for classification quality.

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?

There is a single required parameter with 100% schema description coverage including concrete examples, so the schema does the work. The description adds nothing about how the query string is matched (keyword vs semantic, specificity expectations), so baseline 3 applies.

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: find the US Harmonized Tariff Schedule classification for a product, and names the return payload (candidate HTS codes with official descriptions and base duty rates). This clearly separates it from the landed_cost sibling, which is about cost rather than the code.

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?

"Use when the user wants the code itself rather than a cost" gives an explicit selection condition against the cost-oriented sibling, and the billing note clarifies it is not a charged duty lookup. It stops short of naming landed_cost directly or covering edge cases such as ambiguous product descriptions.

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

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

Beyond the readOnly/idempotent annotations, the description discloses billing behavior, the caching window, and the crucial caveat that partial estimates are provisional with duty_total_bound indicating a minimum. That is real operational context an agent needs before presenting numbers to a user, not a restatement of annotations.

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 purpose and the hts_code-vs-product fork are front-loaded, and every sentence carries content (modes, caveats, billing). It is dense and slightly run-on, packing the estimate_status and duty_total_bound caveats into one long clause, which costs a point.

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 eight parameters, an output schema, and full annotation coverage, the remaining risk is interpretive rather than structural — and the description covers the two failure modes that matter (unpriced classification guesses and partial/provisional totals). An agent has enough to call this correctly and to report results honestly.

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 the baseline would be 3, but the description adds cross-parameter meaning the schema can't easily convey: hts_code takes precedence over product, product never returns prices, and quantity/quantity_unit must match the unit the duty is charged in. It adds workflow-level semantics rather than duplicating field text.

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 first sentence states a specific verb and resource (calculate US import duty and landed cost estimates), and the body clarifies the two operating modes: priced lookup by hts_code vs. unpriced candidate HTS codes by product. It never names the sibling classify_hts, even though the product-to-candidates path overlaps with it, so sibling differentiation is implied rather than explicit.

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?

It gives explicit routing rules: supply hts_code when known, supply product to get candidates, then confirm with the user and call again with hts_code. It also explains why guessing is harmful ('produces confidently wrong numbers') and how to interpret a partial result, plus cost conditions (candidate step free, repeats within ten minutes free).

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

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

Annotations already carry readOnly/idempotent/non-destructive/openWorld, so the description needn't restate safety. It adds genuinely new behavior: a separate "upcoming" block containing entries announced or proposed but not yet in force (so results include non-effective items), sourcing per entry, and a cost note ("Not charged"). It stops short of describing volume/pagination behavior beyond limit.

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?

Three tight sentences with the purpose and scope front-loaded, followed by the non-obvious "upcoming" behavior and the cost/boundary note. No filler or restatement of the title.

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?

Output schema exists so return formatting needn't be explained, and the description still flags the non-obvious shape of the result (an "upcoming" group separate from in-force changes). Parameters, usage triggers, cost, and sibling boundary are all covered for a simple two-optional-param read tool.

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% and both parameters are documented there, including default 30 days and max 50. The description reinforces that "since" filters on Gateway's PUBLISH date rather than effective date, but that distinction already appears in the schema, so it adds little beyond the baseline.

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 ("List US trade policy changes") plus the scope constraint ("since a given date") and enumerates exactly what each entry contains: tariff actions, rate changes, effective dates/expirations, official source. The closing "does not use a duty lookup" separates it from the duty-oriented siblings landed_cost and classify_hts.

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?

Gives two concrete question shapes it answers ("what changed recently", "what is coming") and signals the sibling boundary by noting it does not perform a duty lookup, pointing agents to the cost/HTS tools for that need. No inference is required to select it.

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