Look up an HSN code (Harmonized System Nomenclature, used by Indian GST). Accepts 4-digit, 6-digit, or 8-digit codes (8-digit gets truncated to 6 then 4). Returns {code, description, gst_rate?}. Throws if no match.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | HSN code, e.g. '1006' (rice) or '300490' (other formulated medicaments). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses truncation (8-digit truncated to 6 then 4) and error behavior (throws if no match), which adds value beyond the schema.
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?
Two concise sentences that front-load purpose and include all key behaviors. No redundant information.
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 output schema, the description lists return fields (code, description, gst_rate?) and covers error handling. For a single-parameter tool, this is thorough and includes edge cases (truncation, throwing).
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 coverage is 100% (param already described in schema). The description provides an example ('code, e.g. '1006' (rice)') which adds meaning, but does not significantly expand on the schema's description. Baseline 3 with minor improvement.
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 looks up an HSN code and specifies the valid digit lengths (4,6,8). It does not explicitly differentiate from sibling tools (classify_product, search_hsn), but the name and context imply direct lookup by code.
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 explains acceptable input formats and truncation behavior but lacks explicit guidance on when to use this tool versus siblings (e.g., 'Use this to get details for a specific code, not to search or classify').
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.
Each tool has a distinct input and output: classify_product takes a product name and returns HSN codes; lookup_hsn takes an HSN code and returns description; search_hsn takes keywords and returns matching HSN descriptions. There is no overlap in purpose.
All tool names follow a consistent verb_noun pattern: classify_product, lookup_hsn, search_hsn. The verbs are distinct (classify, lookup, search) and the nouns correspond to the entity (product, hsn).
Three tools is appropriate for a specialized HSN classifier server. It covers the essential operations: classifying a product, looking up a code, and searching by keyword. Not too many or too few.
The tool set covers the main use cases (classify, lookup, search) but could benefit from a tool to list all HSN sections or chapters for hierarchical browsing. However, for the stated purpose of product classification, it is largely complete.