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

With no annotations, the description carries the full burden. It usefully discloses the out-of-scope behavior ('Ids outside your scope are returned as notFound') and hints at caching/refresh via a pointer to GetShipmentStatus, but defers the actual refresh rules rather than stating them, and says nothing about auth or return shape.

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?

Three short, front-loaded sentences with no filler; the scope, refresh pointer, and error behavior each occupy one clause. The middle sentence is slightly hand-wavy but not padded.

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 simple read tool with no output schema and no annotations, it covers the essentials (input cap, out-of-scope handling) but leaves the refresh/caching behavior to an external reference and says nothing about the response format an agent would need to interpret results.

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 schema already documents both parameters; baseline 3 applies. The description's 'up to 100 label ids' merely restates the schema's 'max 100' and it never mentions intentId.

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+resource ('Shipment status for up to 100 label ids') and implicitly positions itself as the batch counterpart to the singular GetShipmentStatus. The batch scope and cap distinguish it, though it relies on the sibling for the actual refresh semantics.

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?

No explicit when-to-use guidance: it never says to prefer this over GetShipmentStatus when querying multiple labels, nor does it state exclusions. The reference to 'Same refresh rules as GetShipmentStatus' presumes the caller already knows that tool, but doesn't route between them.

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