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

With no annotations, the description carries the full burden, and it succeeds. It discloses data-source limitations ('USITC reference data, not a customs ruling'), legal non-effect ('do not establish entry liability'), and measurement caveats ('unit value is not a transaction price'). These are behavioral traits an agent needs before relying on the output.

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 description is dense and front-loaded with a purpose sentence followed by search modes, caveats, citation instruction, and an example. Each sentence contributes value, though the first sentence is a long list of domain-specific fields that could overwhelm some agents.

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 the tool's technical trade-data complexity and lack of an output schema, the description does a strong job: it lists returned fields, search modes, disclaimers, citation requirement, and an example. Some terms like 'HHI floor' and 'retained-board coverage' are left undefined, but this is likely acceptable for a specialized tariff lookup.

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 100%, so the baseline is 3. The description mostly restates the schema's query semantics and adds an example, but does not meaningfully expand on limit or query format beyond what the schema already provides.

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 begins with a specific verb and resource: 'Look up U.S. manufacturing import tariffs', and then enumerates the exact data elements returned (HTS fields, Chapter 99 references, effective duty rate, customs unit value, source shares, HHI). It clearly distinguishes this tariff look-up from the broader sibling tools such as search_site, run_calculator, or ask.

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?

The description gives practical usage guidance: search modes ('Search by keyword, family, or HTS code'), a concrete example ('Try: {"query":"steel"}'), and a required action ('Cite the returned url'). It does not explicitly name alternatives or state when not to use this tool, so it stops 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.