Cancel order

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the risk profile is covered. The description adds real context beyond that: the operation is only valid for pending orders and there is a mandatory human confirmation gate. It does not say what cancellation triggers (refund, notification) or what happens on failure, which keeps it from a 5.

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: the eligibility constraint comes first, the required confirmation workflow second. Every clause carries operational information and there is no filler.

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, no-output-schema mutation with four parameters, the definition supplies the essential preconditions and the confirm workflow an agent needs to call it safely. The remaining gaps — post-cancellation effects, error behavior when status is not pending, and reason semantics — are meaningful but secondary.

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 only 25% (only session_key is documented). The description meaningfully explains when to set confirm=true, which the schema cannot convey via a bare default of false. However, the required 'reason' parameter (3-200 chars) is never addressed, so the description only partially compensates for the coverage gap.

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 narrows scope with a precondition ('that the store has not started yet (status pending)'), which is enough to separate it from siblings such as foran_track_order or foran_order_status. It stops short of naming any alternative tool by name, so it lands just below the top mark.

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 clear use condition (order still pending) and a required call protocol: get customer confirmation first, then pass confirm=true. The negative case (what to do when the store has already started the order) is only implied by the status gate rather than stated, so no explicit alternatives are offered.

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