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

With no annotations provided, the description carries the full burden and delivers: it warns that the result set is intentionally over-inclusive ('most of which do not apply to any one shipment'), discloses that as_of defaults to today, and explains a subtle data-quality trap (treatment_label: null means a gap in the service's own data, not evidence about the treatment type). This is exactly the kind of behavioral context that prevents an agent from drawing wrong conclusions.

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 is front-loaded and every sentence earns its place: purpose, parameter default, result-set caveat with routing, and null-label warning. Though dense, the content is all load-bearing given zero schema annotations and no output schema; nothing is fluff or repetition.

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?

Given no annotations, no output schema, and 0% schema description coverage, the description provides a complete picture: what is returned (base rates, overlapping trade-measure orders, every treatment code), how to use the two parameters, when to choose an alternative, and how to interpret an anomalous return value. Nothing needed for correct selection or invocation is missing.

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%, so the description must compensate, and it does. hs_code gets a format example ('0101.21.00.00'), and as_of gets both a format ('YYYY-MM-DD') and a default value (today). Both parameters are semantically enriched in a way that makes correct invocation possible.

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 opens with a specific verb+resource pair ('Look up base Canadian duty rates') and gives a concrete HS-code format example. It also distinguishes itself from resolve_duty by stating that this returns every treatment code while resolve_duty returns the one that actually applies, so an agent can tell them apart without opening any schema.

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 explicitly names the sibling alternative (resolve_duty) and states the exact condition that should route the agent elsewhere: 'use resolve_duty with a country of origin to get the one that actually applies to a specific import.' This is explicit when-to-use and when-not-to-use guidance, not just implied context.

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