tariff_classificationClassifies products into correct HTS codes from text or documents, automating tariff lookup and ensuring customs compliance in real time.
Pricing: {"unit": "credits", "per_run": 2}
| Name | Required | Description | Default |
|---|---|---|---|
| product_description | Yes | Description of the product used to identify HS/HTS codes. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include openWorldHint: true, indicating flexible inputs. Description adds 'real time' and 'from text or documents' but doesn't disclose limitations, output format, or side effects. The bar is lower due to annotations, but the description still lacks depth on behavior.
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?
Description is short and front-loaded with the action. Includes pricing info which is extra but not harmful. One sentence, no fluff.
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?
With only one parameter and an output schema present, the description is fairly complete for a straightforward classification tool. However, it doesn't specify output format or edge cases, and the pricing info is extraneous. For a simple tool, it's adequate but could mention return format or use cases.
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 covers product_description fullycarsWalkthrough. Description adds minor context ('from text or documents') but doesn't elaborate on input formats or constraints beyond schema.
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 clearly states the tool classifies products into correct HTS codes from text or documents, which is a specific verb+resource. It does not explicitly differentiate from sibling tariff_calc, but the purpose is unambiguous.
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 guidance on when to use this tool versus alternatives like tariff_calc. It mentions 'automating tariff lookup' but doesn't specify use cases, exclusions, or situations where other tools are preferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct (e.g., tariff_calc vs. tariff_classification, search_* vs. sg_*). However, corporate_exception_report and due_diligence_report both produce company reports with overlapping chapter lists and vague descriptions, creating potential confusion for an agent selecting the appropriate report.
Naming conventions are mixed: search_company_candidates and search_region_candidates follow verb_noun, but others use noun phrases (tariff_calc, due_diligence_report) and some use an 'sg_' prefix (sg_chokepoint, sg_visualization). This lack of a consistent pattern reduces predictability.
With 9 tools, the count is well within the ideal 3-15 range and matches the platform's scope—company search, due diligence, supply chain analysis, and tariff handling. Each tool serves a clear purpose without unnecessary bloat.
The surface covers core workflows: company identification (search), deep reporting (due diligence, exception report), supply chain analysis (chokepoint, visualization, risk prediction), and tariff handling (classification, calculation). Minor gaps exist, such as a dedicated tool for fetching a specific company profile, but due_diligence_report largely fills that need.