Search HTS code candidates

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

Annotations already indicate readOnlyHint=true and openWorldHint=false, and the description adds substantial behavioral context beyond that: it cautions that results are 'CANDIDATES' and not legal rulings, explicitly warns about the HTS's use of 'legal terminology,' and describes the expected retry behavior on zero results. This transparency goes beyond just the read-only nature and helps the agent manage expectations about output reliability.

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 tightly written, using sentence case and a clear structure: what it does, a caution, a concrete instruction, and a fallback. The 'IMPORTANT:' emphasis and examples are efficient, though the paragraph could slightly overwhelm new users. Every sentence adds value without fluff, so a 4 is appropriate.

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 tool with only two parameters and no output schema, the description covers all necessary context: input format, expected output, limitations, and error handling. It prepares the agent for edge cases (0 results) and clarifies the tool's role within the larger suite. No critical information is missing for it to be invoked correctly.

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 schema already documents both parameters with 100% coverage (product_description and limit). The description adds high-value guidance for product_description by giving concrete rewriting examples ('pink kids backpack' → 'travel bags of man-made fibers') and explaining the need for legal/material-based nouns. This extra semantic layer justifies a score above the baseline of 3. The limit parameter is fully specified in the schema, so no additional info needed.

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: 'Returns top 8-10 digit HTS code candidates … for a product description.' It clearly differentiates itself from a 'classification ruling' and includes concrete details (MFN/FTA rates, CBP CROSS ruling links). This distinguishes it well from sibling tools like 'calculate_tariff_scenario' or 'watch_tariff_changes' by focusing on the candidate search use case.

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?

Explicit guidance is given on how to prepare input ('rewrite the product description into HTS-style material + use nouns') and how to handle empty results ('retry with 2-3 different phrasings'). It also clarifies the tool is for 'pre-broker screening, not a classification ruling,' which sets expectations. However, it doesn't explicitly name when to prefer a sibling tool, and the 'when not' is only implied by the disclaimer, not fully elaborated.

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