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

Annotations already flag destructive/non-idempotent/open-world, but the description goes well beyond them: real EUR charge excl. VAT, no-retry semantics, possible duplicate labels after a timeout, non-atomic same-instance duplicate guard that fails across Worker instances, and the ~17:00–20:00 cancellation window. This is exactly the behavioral context an agent needs before spending money.

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 the 'WRITE, COSTS MONEY' signal and organized as risk → cost → retry → confirmation, with no filler sentences. It is dense and slightly repetitive (checking shipcloud after an uncertain result is stated twice) and packs multiple clauses per sentence, but every sentence carries operational weight.

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 10-parameter, nested-object, money-spending tool with no output schema, the description covers cost, side effects, idempotency hazards and the customs exclusion thoroughly. The remaining gap is return values — with no output schema, the agent is not told what comes back (label document/URL, shipment id), which matters for a purchase call.

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 baseline is 3; the description still adds meaning by tying reference_number to duplicate detection after a timeout and by stressing it must be unique and serialized per reference. The confirm parameter's 'ask first, do not assume' framing reinforces but largely restates the schema text, so it does not fully exceed the schema's own guidance.

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 opens with a specific verb+resource ('create a shipment AND buy its shipping label') and immediately qualifies scope with 'create_shipping_label=true', which separates it from shipcloud_create_prepared_shipment. 'POST /shipments' anchors it to the underlying endpoint, so an agent knows exactly which operation this is.

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 explicit routing: fetch the price first from shipcloud_get_shipment_quote, confirm only after the user agreed to be charged, cancel via shipcloud_delete_shipment before the carrier cut-off, and on uncertain results check shipcloud_list_shipments before retrying. It also states a hard exclusion ('shipments needing customs papers are not supported here') and the sandbox-vs-live distinction.

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