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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds genuine behavioral context beyond them: what the response contains (ranked modes with reasons plus distance) and the business constraint that it 'does not count toward the estimate allowance'.

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 tight sentences, each carrying distinct information (outputs, workflow ordering, international edge case, allowance note). The core capability is front-loaded and nothing is wasted.

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 no output schema, the description steps in to explain the return values (ranked modes, reasons, distance). Combined with the 100%-covered input schema and the workflow guidance, an agent has everything needed to call it 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 100%, so all four parameters are already documented. The description's mentions of 'city names or ZIPs' and U.S. lanes only echo what the schema's origin/destination descriptions already say, adding no new syntax or format detail. Baseline 3 applies.

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?

Uses a specific verb ('Rank') with the exact resource (the seven named freight modes) and states the two concrete outputs: ranked modes with reasons and lane distance in miles. It clearly differentiates itself from the estimate_* siblings by framing itself as the routing/distance step that precedes 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?

Gives explicit ordering ('Use it first when you only have city names or ZIPs, then pass the distance to an estimate_* tool'), which names the alternative and the condition that selects it. It also handles the edge case by stating that international lanes return ocean/air routing instead.

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