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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower, yet the description adds substantive model behavior: which costs are included (duty on freight itself, cost of capital in transit, lost profit) and that it returns the break-even weekly lost profit. It does not state assumptions are overridable defaults or how the result is presented, keeping it below 5.

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?

Two sentences, both load-bearing: the first front-loads the usage condition and the comparison scope, the second names the returned break-even figure. No filler or restatement of the title.

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 10 parameters, no output schema, and a non-trivial cost model, the description supplies the decision context and the key return value (break-even weekly lost profit), which is exactly the gap left by the absent output schema. It could add a note that transit-day and rate inputs are defaulted assumptions to be overridden with user data.

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; the description adds conceptual meaning beyond the schema by explaining the economics behind the non-obvious inputs — 'cost of capital tied up in transit' maps to capital_rate_percent and 'profit lost while stock is unavailable' to lost_profit_per_week. It stops short of touching the freight-rate or transit-day inputs individually.

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 and resource ('compares the two on total landed cost') with an explicit scope ('air and sea freight from China'), which distinguishes it from the sibling estimate_landed_cost that handles landed cost for a single mode. An agent can pick this tool without opening the schema.

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?

Opens with 'Use when the user is choosing between air and sea freight from China', giving a clear triggering condition and the decision context. It does not name a sibling alternative or state when not to use it (e.g. for a single-mode landed-cost calculation), so it falls short of a full 5.

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