GroundTruth: 2026 US Tariff & Landed Cost

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the estimate includes all stacking layers plus MPF/HMF and that the response includes official sources and an as-of date, but it says nothing about permissions, rate limits, accuracy caveats, or whether the operation is read-only.

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 compact sentences with the core purpose front-loaded, followed by the key input constraint and output note. Nothing is wasted, though the return-value sentence could be folded in slightly more tightly.

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 7-parameter computation tool with no annotations, no output schema, and only 29% schema description coverage, the description is too thin. It explains what is computed and partially what is returned, but leaves the agent without guidance on most inputs or on input format expectations.

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 only 29% and the description does not mention any input parameter directly. It hints at product_description via 'plain product description' and broadly implies freight/insurance/broker_fee through 'landed cost,' but origin_code, arrival_mode, and declared_value receive no clarification, leaving the low coverage uncompensated.

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 uses a specific verb (Estimate) and resource (total US customs duty, MPF/HMF, landed cost), and scopes it to a plain product description with no HTS code required. This clearly distinguishes it from the sibling list_tariff_categories tool, which is a browsing operation rather than a computation.

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 a clear usage context: 'from a plain product description' and 'No HTS code required,' which tells an agent this is the right tool when no classification code is available. It does not explicitly state when not to use it or name the sibling alternative, so it falls just short of a 5.

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?

With no annotations, the description carries the full behavioral burden. It discloses the shape of the returned reference data (categories, country layers, fees, notes), which is useful, but says nothing about whether the data is static, how large the result is, or how it should be combined with compute_tariff. For a read-only listing tool this is adequate but thin.

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?

A single tight sentence with the verb front-loaded and no filler. It is a dense noun pile, but every listed item earns its place by telling the agent what data is available.

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?

No output schema or parameters exist, and the description compensates by enumerating the fields the listing returns, which is the main thing an agent needs here. The only real gap is the absence of guidance on how this reference list relates to compute_tariff.

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?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate, and it correctly does not invent parameter details.

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 names a specific verb ('List') and enumerates the resource contents (2026 US tariff product categories, origin-country layers, MPF/HMF fees, notes), so an agent knows exactly what it returns. It does not explicitly contrast itself with the sibling compute_tariff, leaving the list-vs-compute distinction to inference.

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?

There is no statement of when to use this versus compute_tariff, nor any prerequisites or exclusions. Usage is only weakly implied by the verb 'List', which suggests reference-data retrieval, but the agent gets no explicit routing guidance.

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