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

With no annotations, the description fully carries the behavioral disclosure burden and does so richly. It explains the lexical classifier fallback, warns that vague descriptions return a likely-wrong HS code, instructs agents to never quote inferred codes as user-provided, and clarifies that destination findings are unaffected by classification doubt. These are meaningful behavioral traits beyond what any schema or annotation would show.

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 long but well-structured with clear paragraphs, IMPORTANT callouts, an Args section, and examples. It front-loads the core purpose before adding caveats. Some redundancy exists (e.g., the final use case restates the opening purpose), but the length is justified by the high-stakes, complex domain and the need to warn about classifier pitfalls.

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 complexity, the description covers all essential aspects: input requirements, jurisdiction logic, classification uncertainty, return values (license, risk, policies, reasons, flags), and usage examples. An output schema is present, so the description does not need to enumerate every return field; it provides enough context for an agent to invoke the tool correctly and interpret results 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 description coverage is 0%, so the description must compensate, and it does. It explicitly lists each parameter, gives formats (ISO 3166-1 alpha-2, ECCN example, HS code digit range), acceptable jurisdiction values, and the 'at least one of' constraint. It also includes multiple usage examples that map parameters to real inputs, making parameter semantics far clearer than the raw 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 opens with a specific verb+resource combination: 'Screen goods for export-control restrictions to a destination country.' It clearly explains the tool's combined function (goods classification + destination restriction status) and differentiates it from siblings by mentioning the multi-jurisdiction and license-determination aspects, which are not covered by other tools like goods_classify alone.

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 gives a concrete use case ('Can we ship integrated circuits to Russia?') and provides guidance on when to use jurisdiction='ALL' versus a specific jurisdiction. It also warns against using goods_description when ECCN/HS code is available. However, it does not explicitly name alternative sibling tools or say 'use X instead when...', so it stops short of full when-not/alternatives guidance.

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