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

Adds substantial context beyond the destructive/non-idempotent annotations: Shippit allocates a carrier, emails the recipient tracking notifications unless suppressed, and "creating twice creates two orders" — a critical duplicate-creation warning aligned with idempotentHint=false. It also discloses that validate returns a suggested address on rejection.

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 tag and the core action, then the booking-flow caveat, then validation and idempotency. Dense but every sentence carries operative information; only the repeated booking note feels slightly heavy.

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 25-param mutation with no output schema, the description covers the safety profile (confirm, duplicate risk), side effects (emails, carrier allocation), validation behavior, and scope exclusions (international). An agent has enough to call it safely without guessing about return values.

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?

At 64% schema coverage, the description earns credit by clarifying the courier_type vs courier_allocation mutual choice, confirm semantics, and that validate defaults to true. These are the highest-risk fields and the description explains them well beyond the schema's per-field text.

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?

Opens with a specific verb+resource and scope: "WRITE: create a domestic shipping order in Shippit." It explicitly delineates against siblings by naming shippit_label_order and shippit_book_orders as the tools that later book standard/express/click-and-collect orders, and rules out priority/on-demand orders.

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 concrete preconditions and exclusions: requires confirm:true, international/customs orders are unsupported, and validation defaults reject mismatched suburb/postcode. It clearly routes post-create booking to shippit_label_order and shippit_book_orders. It stops short of describing when to prefer shippit_get_quotes or an upfront quoting flow before creating.

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