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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds genuinely new consequences: a real request is sent to the carrier, it cannot be cancelled through this server, and carriers may bill for pickups. That is exactly the risk context an agent needs before a destructive write.

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 dense paragraph led by the WRITE marker, with the highest-risk fact (irreversible, billable) placed early and no filler sentences. Every clause carries operational information.

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 destructive, non-idempotent mutation with no output schema, the description covers irreversibility, billing, confirm gating and shipment scoping. It omits what the call returns (presumably a pickup request id the agent would need for follow-up), which is the main remaining gap.

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 83%, so the baseline is 3, but the description adds semantics the schema only hints at: the omitted-shipment_ids default scope and the return-shipment exclusion. The confirm gating rationale is echoed from the schema rather than new, so it is not a full 5.

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?

"WRITE: order a carrier (dpd, gls, hermes or ups) to pick up parcels at an address in a time window" gives a specific verb, resource, enumerated carriers and the two defining inputs. It is unmistakably distinct from sibling creation tools like shipcloud_create_shipment_with_label or shipcloud_create_prepared_shipment.

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 clearly states the conditions that select behavior: with shipment_ids only those parcels, without them all not-yet-picked-up shipments, and return shipments cannot be picked up at all. It also gates invocation on explicit user agreement via confirm=true. It does not name a sibling alternative (e.g. get_pickup_request to check status), so it stops short of a 5.

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