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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds value beyond that: it names the underlying data source (IFC's Indian import duty database), the result cap (up to 10 matches), and the returned unit (8-digit codes with descriptions). It stops short of describing ranking/relevance or what an empty result means.

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?

A single front-loaded sentence with no filler: verb and data source first, then input modes, then output shape. Every clause carries information an agent needs.

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 one required parameter, no nested objects and no output schema, the description adequately covers input modes, data scope and return shape, and annotations cover the safety profile. Only minor gaps remain, such as result ordering or whether partial/no matches are possible.

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% and the schema already explains the single parameter, so the baseline is 3. The description earns a bump by supplying concrete example queries ("bluetooth speaker", "office chair") that show the expected phrasing granularity, which the schema's terse 'Product words or the start of an HS code' does not convey.

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?

States a specific verb and resource: searches IFC's Indian import duty database for HS codes, with two concrete input modes and the result shape (up to 10 matching 8-digit codes). It is clear what the tool does, but it never names or contrasts itself with the sibling lookup_hs_code, which is the natural point of confusion for an agent choosing between them.

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 enumerating the two acceptable query forms (product words such as "bluetooth speaker", or the leading digits of an HS code), which is genuine guidance on how to invoke it. However it gives no explicit when-to-use/when-not conditions and does not point to lookup_hs_code or estimate_landed_cost as alternatives, so routing is left to inference.

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