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

Annotations already disclose destructiveHint=true and idempotentHint=false. The description adds meaningful behavioral context beyond that: nothing is charged and the card authorisation is released, which directly informs the buyer of the financial consequence of cancelling.

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?

Two compact sentences with zero waste. The actor and restriction are front-loaded, and the financial consequence follows immediately.

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 simple one-parameter mutation with annotations covering safety and idempotency, the description supplies the condition and financial outcome needed to call it correctly. It could do slightly more by clarifying post-cancellation order status, but it is largely complete.

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?

The single parameter, order_id, has 100% schema description coverage including an example format. The description adds no additional parameter semantics beyond what the schema already provides, so the baseline of 3 applies.

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 (cancel) and resource (order), plus the actor (buyer) and a key condition (not delivered). It is clearly distinct from retrieval siblings like get_order/my_orders and from delivery-oriented siblings like accept_delivery, though it does not explicitly name alternatives.

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?

The phrase 'order that was not delivered' gives a clear use condition and implicitly excludes delivered orders, which are handled by tools like accept_delivery or redeliver. No explicit alternative is named, so it falls 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.