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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral context: it returns both series aligned month-for-month, changes, ratio, and a stated finding; reveals special landed_cost calculations for two origins on a specific commodity; explains data sources (nationwide receipts for duties); and states no API key is required. No contradictions with annotations.

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 longer than average but every sentence contributes. It is front-loaded with the core action, then gives examples, then covers an advanced feature (landed_cost) and constraints. The length is justified by the tool's complexity, though it could be slightly tightened (e.g., bullets for the examples).

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 8 parameters, no output schema, and no nested objects, the description must be self-sufficient. It explains return values (series, changes, ratio, finding), the special landed_cost/headroom output, data source caveats (burden_pct/duty_usd not for gateway), and operational guidance (call twice for more than two). This is complete enough for an agent to invoke the tool correctly.

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 only 25% (just origin/commodity have descriptions), so the description carries the burden. It clarifies the semantics of 'kind' (origin/commodity/gateway), 'measure' (weight, value, unit value, tariff burden, duty paid), and 'subject_a/subject_b' (two origins, commodities, or gateways). It also explains constraints like same-kind requirement and gateway limitations, which are not in 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 starts with a specific verb+resource: 'Put two subjects on the same axis...compute the difference' and clearly enumerates the supported subject types (origins, commodity chapters/HS6 codes, US gateways) and measures. It fully distinguishes this tool from siblings like origin_profile or tariff_burden by focusing on side-by-side comparison, and even gives concrete example questions.

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 explicitly states when to use this tool: 'Use for "is trade shifting from China to Vietnam"...' and provides multiple real-world queries. It also gives important constraints: subjects must be the same kind, compare more than two by calling twice, and burden_pct/duty_usd are not available for gateways. This is clear, actionable guidance.

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