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

Annotations already cover the safety profile (readOnly, non-destructive, non-idempotent, closed-world), and the description adds substantial behavior on top: the failure mode (returns available:false with the reason), the pricing basis (river miles), the minimum shipment threshold, the benchmark nature of the result, and a quota cost of one estimate against a monthly FreightFA 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 dense sentences, front-loaded with the purpose and then the qualifying conditions. Every sentence carries load (eligibility, failure mode, pricing basis, quota), though the eligibility clause packs several conditions into one long sentence.

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 still explains what comes back (a directional benchmark, or available:false with a reason) and the constraints that govern whether a price exists at all. For a 5-required-parameter estimate tool with full schema coverage, nothing an agent needs is missing.

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 100%, so the baseline is 3, but the description adds meaning the schema does not: distance is interpreted as river miles, weight must clear roughly 1,500 short tons / 3,000,000 lb for a barge-load, and commodity_type is implicitly constrained to bulk goods that barges carry.

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?

States a specific verb (estimate) plus the resource (inland waterway barge freight rate) and enumerates the five inputs that drive it. It also roots the estimate in a named source (USDA's weekly downbound grain barge rates), which distinguishes it from the rail/truckload/intermodal estimators in the sibling list.

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 eligibility rules: priced only when both ends are Mississippi/Illinois/Ohio River ports, the lane is downriver, and the shipment is at least one barge-load. It even points at recommend_mode for deriving distance. It stops short of naming which sibling estimator to use when the barge conditions fail, so routing to rail or truckload is left implicit.

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