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

Annotations already declare readOnlyHint and openWorldHint, and the description meaningfully adds that position resolves to lower_landed_cost, higher_landed_cost, or unknown, and that a missing figure surfaces as "Being measured." That partial-data behavior is genuinely useful for interpretation. It stops short of explaining data freshness or how the public market read is sourced.

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 four sentences are short and the enum values and missing-data note are placed late but visible. The opening fragment "Keyed." consumes prime first-position space without conveying anything an agent can act on, so the structure is tighter than it is informative.

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 carries the burden of describing return values, and it does name the three figures and the position enum. It leaves unclear what exactly defines lower_landed_cost versus higher_landed_cost relative to the official rate, and what "public market read when one exists" means in practice, which matters for a comparison tool.

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 both currency parameters and the access_key alternative are already documented in the schema. The phrase "for one corridor" adds mild context that from/to form a pair, but nothing is said about access_key handling or about constraints on valid pairs. Baseline 3 applies when the schema does the heavy lifting.

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?

"For one corridor, the rail's own published rate beside the official rate and a public market read" does describe the returned content, but there is no explicit verb (returns/compares) and the leading "Keyed." is unexplained jargon. It does not differentiate itself from close siblings such as get_corridor_rates, price_routes, or swapeazi_landed_cost, which appear to occupy adjacent territory.

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 implies a single-corridor lookup but never states when to call this instead of get_corridor_rates, price_routes, or swapeazi_landed_cost. No prerequisites, no exclusions, no selection criteria are given, leaving the agent to infer routing from sibling names alone.

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