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

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable behavioral context: asynchronous execution, the async:true requirement to avoid timeouts, and the specific data sources cross-referenced. This goes beyond the structured annotations without contradicting them.

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, each earning its place: purpose, method/data sources, inputs/outputs, and async requirement. No filler or repetition, and the 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 complexity, the description covers all essential aspects: purpose, data sources, input categories, output nature, and the critical async requirement. With an output schema present, return values are already structured, so no further detail is needed.

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 80%, so baseline is 3. The description reinforces key inputs (shipment IDs, company identifiers, routes) and adds crucial guidance that async:true is required, which goes beyond the schema's optional indicator and adds meaningful usage semantics.

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 states a specific verb+resource: 'detect unauthorized diversion of dual-use technologies' and details cross-referencing of specific data sources (shipment manifests, EU sanctions lists, ICAO/IMO transport data). This clearly distinguishes it from sibling tools like dual_use_export_risk_mapper by focusing on diversion monitoring.

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?

Provides clear context: intended for COO persona monitoring and mandates async:true to avoid 402 timeouts. However, it does not explicitly name alternative tools or exclusion cases, stopping short of full guidance.

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