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

The description adds one real behavioral fact beyond the annotations: 'Stores nothing,' which matters for an agent handling untrusted input. The annotations already carry readOnly, idempotent, non-destructive and closed-world hints, but the description does not disclose confidence/uncertainty behavior or that the result is a heuristic guess with partial failure modes.

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?

A single sentence front-loads the classification purpose and ends with the storage caveat; no filler, no restating 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?

For a one-parameter, read-only, closed-world classifier with full schema coverage and no output schema, the description is nearly sufficient. The main omission is what the response contains (e.g. type, carrier name, confidence/validity flag), which an agent must know to interpret results since there is 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% and the single parameter's description 'Container, bill of lading or booking number' already mirrors the tool description. The description adds no format detail (e.g. whitespace, hyphens, case sensitivity, or the 3-64 length constraint's practical implications), so it stays at the baseline.

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 uses a specific verb ('Guess whether') plus the exact resource ('a number') and enumerates the three reference kinds it classifies (container with ISO 6346 check digit, bill of lading, booking number), plus carrier identification. No sibling tool does classification, so its role among list_*/get_* siblings 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?

It makes the input condition clear ('whether a number is...'), which implies when to call it: when you have an unidentified reference string. However, it names no alternatives and gives no exclusions, e.g. that it is unnecessary for already-known shipment IDs or that get_shipment should follow if a match is found.

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