HSN Classifier

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

With no annotations, the description carries full burden. It discloses the return structure, that it is best-effort, always returns a result, and that 'best' may be null. This provides good behavioral insights, though it could mention if the tool has any side effects or performance characteristics.

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 two sentences, each serving a clear purpose: stating the action and return shape, then adding a behavioral qualifier. No unnecessary words, and the key information is front-loaded.

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 simplicity (one parameter, no output schema, no annotations), the description fully covers what the tool does, how it behaves, and what it returns. It explains the return fields and the possibility of a null 'best'. No gaps identified.

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% with a clear parameter description including an example. The tool description does not add significant additional meaning beyond the schema, so a baseline score of 3 is appropriate.

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's action ('Classify a product name'), resource, method ('via keyword scoring'), and return shape. It distinguishes from siblings 'lookup_hsn' and 'search_hsn' by specifying the classification approach and that it returns a best-effort result with alternatives.

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 implies usage by stating it classifies product names into HSN codes, but it does not explicitly explain when to use this tool versus the sibling tools 'lookup_hsn' or 'search_hsn'. There is no guidance on prerequisites or exclusion criteria.

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

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

Without annotations, the description fully discloses key behavioral traits: accepted code lengths (4,6,8-digit), truncation behavior for 8-digit codes, return fields ({code, description, gst_rate?}), and error handling (throws if no match). No contradictions.

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 covering purpose, input constraints, behavior, return, and errors. All information is front-loaded and essential, with no wasted words.

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 a single parameter, no output schema, and no annotations, the description provides complete context: purpose, input rules, return structure, and error condition. No gaps identified.

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 covers the parameter fully (100% coverage), but the description adds meaning beyond the schema by specifying accepted digit lengths and truncation behavior, which helps the agent understand input constraints.

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?

Description clearly states it looks up an HSN code, specifies the code length (4,6,8-digit), and mentions it's for Indian GST. It also indicates the return structure and error behavior, effectively distinguishing it from sibling tools like search_hsn and classify_product.

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 implies use when you have a specific HSN code to look up, but does not explicitly state when to use this tool versus alternatives (e.g., use search_hsn for partial matches or classify_product for product classification). No when-not guidance provided.

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

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

With no annotations, the description discloses ranking behavior, limit parameter (default 10, max 50), and that results are ranked. Does not mention handling of empty queries or no matches, but covers key behavioral aspects.

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?

Three sentences that each add value: purpose, parameter detail, and usage guideline. No unnecessary words or repetition. Front-loads the core action.

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?

Covers purpose, parameter behavior, and usage context well. However, lacks description of the return value structure (e.g., fields like code, description, relevance score) which is important since there is no output schema defining it.

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%, so baseline is 3. Description adds value by explaining the limit parameter's behavior (default, max, ranking) and the purpose of the query parameter (free-text). Exceeds baseline by providing context 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?

Clearly states 'Free-text keyword search across HSN descriptions' with specific verb (search) and resource (HSN descriptions). Includes a use case ('when you have a product name but not a code') that distinguishes it from sibling tools classify_product and lookup_hsn.

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?

Explicitly says 'Use this when you have a product name but not a code', providing clear context. Lacks explicit exclusion of alternative tools but the guidance is sufficient for typical usage.

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