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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=true, so the write/destructive profile is covered. The description adds non-obvious behavior the annotations lack: the partial-fulfillment semantics and that Order Desk derives tracking_url when omitted. It leaves the odd destructiveHint=true on an additive operation unexplained.

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?

Four short sentences, all load-bearing, with the operation type and target front-loaded before the modeling rules and the endpoint. No filler.

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 7-param mutation with no output schema, it covers what the agent most needs: write semantics, partial-fulfillment modeling, and optional-field derivation. It omits response/return behavior and any error or duplicate-shipment considerations, which would have made it fully self-contained.

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 description coverage is already 86%, so the schema carries most param meaning (baseline 3). The description still adds value by explaining the optional tracking_url derivation and reiterating the 'n/a' convention for tracking_number, but says nothing about cost, weight, or shipment_method.

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 ('record a shipment... against an order') and tags it 'WRITE', which immediately separates it from read siblings like orderdesk_list_order_shipments and the other add_* tools.

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?

Gives real modeling guidance: one shipment per parcel, multiple shipments = partial fulfillment, and the 'n/a' fallback for missing tracking numbers. It does not, however, name when to prefer a sibling (e.g., list vs add) or note any preconditions on order state.

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