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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description adds real behavioral context beyond them: default status=active, newest-first ordering, all-arguments-optional, the returned field set, has_more/next_cursor, and the 1-100 limit range. It does not mention rate limits, permission requirements, or whether archived results are ever included implicitly, which keeps it from a 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?

Front-loaded with purpose and search capability, then usage routing, then return shape and paging - a sensible order with no filler sentences. The inline enumeration of all 17 return fields is the densest part and slightly list-like, though it is informative rather than redundant.

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 an 11-parameter, all-optional list tool with no output schema, the description carries everything needed: what it returns, the pagination contract, defaults, and where to go for adjacent queries. Nothing an agent needs to invoke it correctly or chain a follow-up call is missing.

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 earns above that by explaining cross-parameter mechanics the schema cannot - that next_cursor is passed back as `cursor` to get the next page, that the default page size is 20 within limit 1-100, and that status defaults to active. The remaining filter semantics (q fields, ISO 8601 windows, eta_risk) are already fully documented per-parameter in the schema.

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 ('List or search the company's own tracked shipments') plus ordering ('newest first') and scope ('company's own'). It explicitly separates itself from get_shipment, arriving_soon, delayed_shipments and list_shared_shipments, so an agent can distinguish it from every relevant sibling without opening a 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?

Provides both when-to-use (find by free-text q, or filter by status/carrier/phase/tag/ETA window/eta_risk) and explicit routing to alternatives with the condition that selects each: get_shipment for one shipment's detail, arriving_soon for next N days, delayed_shipments for slipped ETAs, list_shared_shipments for third-party shares.

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