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

Annotations already disclose destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds value beyond them with an auth requirement ('Requires an API key') and a state precondition (unpaid only), though it doesn't state reversibility or downstream effects.

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 short sentences, zero filler, with the precondition and auth requirement front-loaded after the core action. Nothing is redundant.

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 destructive mutation with annotations already covering safety and no output schema, the description supplies the key missing context: the precondition and the API-key requirement. It could go further on what cancellation implies for the order afterwards, 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?

Schema description coverage is 0%, but the single parameter is named order_id with format=uuid and a regex pattern, making its meaning effectively self-evident. The description adds nothing about the parameter, so it does not compensate for the coverage gap, but the gap is minimal for one self-describing param.

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 ('Cancel an order') and adds a scope constraint ('that has not been paid yet'). It is clearly distinguishable from siblings like approve_order, deliver_order, or open_dispute, but it does not name any sibling as the alternative path.

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 a usable precondition (order must be unpaid), which implies when the tool applies. However it offers no explicit alternative guidance for paid orders — e.g., whether open_dispute is the right sibling in that case — so the agent must infer the fallback.

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