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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so safety is covered. The description usefully adds behavioral constraints beyond them: unknowns stay unresolved, user review states are treated as scenario assumptions, and subtotals must not be extrapolated to a final duty. It does not describe the response shape or error behavior, so it exceeds the annotation baseline only modestly.

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?

Four sentences, front-loaded with purpose and then the operating rules, with essentially no filler. The density of domain jargon is high, but every sentence contributes a distinct instruction or constraint.

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 21-parameter tool with no output schema and 19% schema coverage, the description is too thin: it never explains what the 'duty stack' review returns, how the status enums feed the result, or how unresolved layers surface. The behavioral rules it does give are valuable but do not close the gap for a tool of this complexity.

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 19% across 21 parameters, so the description must carry the burden and largely fails to. It names customsValue and entryDate but omits hsCode and origin (both required) and says nothing about the nine status enums (section232Status, usmcaStatus, chinaSection301Status, etc.) or the measurement fields that drive the review.

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 states a specific verb and resource ('Review an import duty stack') and enumerates the components it handles (official sources, known subtotals, missing inputs, unresolved applicability). It is clear what the tool does, but it never names or distinguishes itself from the sibling lookup_hts_base_rate, so an agent must infer the boundary between base-rate lookup and full-stack review.

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 are real usage rules - required inputs ('Provide the real USD customs value and entry date') and an exclusion ('Do not infer a final duty from a known subtotal') - plus the treatment of unknowns. However, it gives no explicit when-to-use vs the sibling tool or any other alternative, leaving routing to inference.

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