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

With no annotations, the description carries the full burden and does add real value: it discloses the authentication modes (API key, OAuth, x402 payment) and the return structure (import charges vs. landed cost). However, it omits error behavior, what a 'supported' layer means, and the fact (buried in the schema) that unrecognized fact keys are rejected and that unimplemented claims return a review response rather than a total.

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 sentences, no filler, and the output-shape sentence earns its place. Minor flaw: the definition leads with the access/payment sentence rather than the purpose, so the most decision-relevant content is not front-loaded.

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 13-parameter tool with deep nested objects, one enum, no output schema, and no annotations, the description is far too thin. It explains the result shape but leaves the agent guessing about the two distinct ways to declare special treatment (facts vs. claims vs. chapter99), quota handling, and the many undocumented scalar parameters.

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 38% – well below the 50% threshold – so the description must compensate, and it does not: hts, country, value, mode, as_of, quota_state, product_content, component_values_usd, alcohol_by_volume_percent, and quantities receive zero mention. The one arguably central argument, facts, is documented only inside the schema, not the description.

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+resource+scope: 'Calculate supported US duty layers and fees for one import line'. An agent can tell this is a duty computation, not a lookup (lookup_tariff) or a comparison (compare_tariff_codes). It stops short of naming siblings or distinguishing itself from assess_import_entry, and 'supported' is left unqualified.

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?

No when-to-use / when-not-to-use guidance and no named alternative. The clause 'without estimating fact-dependent treatment' hints at a boundary but does not tell the agent which tool to reach for when facts are unknown, or how this differs from assess_import_entry or replay_tariff.

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