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

With no annotations, the description carries the transparency burden. It adds useful context: per-call pricing, 'AI-synthesized' data provenance, and global coverage. However, it does not mention authentication, rate limits, response format, or whether any actions have side effects, which is a moderate gap for a tool with 12 endpoints.

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 well-structured with a clear title, coverage statement, and a bulleted endpoint list. Each line is concise and serves a purpose (name, price, function). It is front-loaded and does not include irrelevant details.

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 complex tool with 12 actions and 26 parameters, the description gives a useful overview and per-endpoint summaries. However, it lacks return-value details and deeper differentiation between similar actions (e.g., 'compliance' vs 'sanctions'), so an agent might not fully understand what each endpoint returns. The endpoint summaries are sufficient for basic selection but not for nuanced edge 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?

The input schema provides 100% coverage with detailed descriptions for all 26 parameters, so the baseline is 3. The tool description does not add parameter-level semantics (e.g., which parameters apply to which action), but the endpoint list provides some contextual linkage. This is adequate but not additive beyond the 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 identifies the tool as a global trade intelligence API with a list of specific endpoints (classify, tariff, landed, etc.), each with a one-line purpose. This provides a specific verb-resource mapping and distinguishes it from sibling tools by domain.

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 endpoint list acts as usage guidance, linking each action name to its function (e.g., 'tariff ($0.12): Tariff rates by HS code and country pair'). While there are no explicit 'when not to use' statements, the mapping is clear enough for an agent to select the appropriate action. Minor gap: no guidance on preferring one action over another for overlapping domains like sanctions vs compliance.

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