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

Annotations already cover read-only, idempotent, and non-destructive hints. The description adds valuable context: it discloses that uncertified families return empty results, legacy rows are not fallback, and provides a structured return shape (query and results categories). It also notes the tool is FREE. These go beyond annotation defaults, earning a 4.

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 compact and front-loaded with the primary action and scope. It then covers behavioral constraints, return format, and related tools in a logical sequence. Every sentence adds distinct value; no filler or redundancy.

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?

For a one-parameter search tool without an output schema, the description provides sufficient context: what is searched, what is excluded, the result envelope, and sibling alternatives. It could mention result ordering or pagination, but the current detail is adequate for correct invocation.

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 for the single parameter is 100%, but the description enhances meaning by providing concrete examples ('maersk', 'mumbai', 'hapag-lloyd') and clarifying the types of search terms relevant. This guidance helps the agent construct effective queries beyond the schema's generic 'Search term' description.

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 clearly states the tool's function: 'Search current customer-published ShippingRates datasets by keyword.' It enumerates specific matchable entities (port codes/names, carrier identities, transit services, local-charge names/carriers) and distinguishes itself from siblings by naming dedicated tools for structured lookup. The scope 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 provides alternatives: 'Use shippingrates_port for structured port lookup by UN/LOCODE, shippingrates_lines for full carrier listing.' It also implies when not to expect results by stating that uncertified families remain empty and legacy rows are never used as a fallback, guiding the agent on appropriate invocation.

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