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

Annotations already declare non-idempotent and destructive, but the description adds consequences beyond them: each call creates a new record, a duplicate results from a second call, and MarketTime may notify the customer of tracking details. That side-effect disclosure is genuinely useful; the one gap is no mention of failure modes or auth requirements beyond the account-scope note.

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 compact clauses, all front-loaded with the WRITE classification first, the side-effect risk second, the precondition third, and the endpoint last. No redundant restatement of the title or schema.

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?

Behavioral risk for a destructive, open-world mutation is well covered and no output schema exists to explain, but with 8 parameters at 50% description coverage the definition leaves half the input surface unexplained. Adequate for safe invocation, incomplete for correct parameterization.

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 only 50%, so the description is expected to compensate for undocumented fields — and it adds nothing. Four parameters (notes, invoice_amount, invoice_number, tracking_number) are undefined in both schema and description, and the description only gestures at 'tracking' generally.

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 the exact verb ('add a shipment with tracking to an order'), the target resource, and the account scope ('manufacturer accounts only'). It also implicitly distinguishes itself from the read-only sibling markettime_list_order_shipments by calling itself the write counterpart.

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?

Explicitly routes the agent: 'Check markettime_list_order_shipments first' names the alternative tool with a clear precondition, and 'manufacturer accounts only' gives an exclusion condition. The duplicate-creation warning ('calling it twice makes a duplicate') reinforces when not to re-call.

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