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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavior beyond annotations: unsupported lanes return empty arrays, unpaid calls return 402 with payment instructions, and the return payload includes detailed fields such as rate_low/mid/high and trend. No contradiction with annotations.

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 description is relatively long, but it is well-structured with a clear opening purpose, distinguishing clarifications, payment info, and a detailed return format. The return structure is necessary because no output schema is provided. Each sentence adds value, though a tighter format could improve conciseness.

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 no output schema, the description fully compensates by detailing the return object and nested rates array fields. It covers edge cases (empty array, 402), differentiates from siblings, and provides operational requirements (payment). This is a complete description for a tool of this complexity with four parameters and no output schema.

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%, with each parameter having a description and examples for origin and destination. The description only adds the phrase 'optionally filtered by container type,' which mirrors the schema. It does not introduce new parameter semantics beyond what the schema already provides, so the baseline of 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?

The description opens with a specific verb+resource: 'Get current certified freight benchmark observations between two ports, optionally filtered by container type.' It clearly distinguishes this from carrier spot quotes and contracted rates, and contrasts with sibling shippingrates_total_cost. The scope is precise and the tool's identity as a benchmark lookup is unambiguous.

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 explicitly states when to use this tool versus alternatives: 'For a published multi-component estimate, use shippingrates_total_cost.' It also clarifies that these are official indices, not spot quotes, and that unsupported lanes return an empty rates array. Payment requirements are disclosed, giving clear operational context.

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