Cancel Rappi order

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

Annotations already declare readOnlyHint=false and destructiveHint=true. The description adds valuable behavioral context beyond annotations: 'May refund' (consequence) and 'Guest tokens rejected' (auth requirement). These are not present in the annotations, so the description contributes meaningfully.

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?

The description is four short fragments, each carrying distinct info: gating, refund, mutations/intent, guest token rejection. It's front-loaded with the 'Gated' caveat and has no fluff. Efficient and structured.

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 cancellation tool, the description covers gating, refund, and auth, but omits operational details such as when an order is cancellable (e.g., status limits), what the response/result format looks like (no output schema), and potential error cases. The destructive nature is covered by annotation, but the description lacks enough to handle real-world invocation nuances.

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 33% – only explicit_user_intent has a description. The description reinforces that parameter ('Requires ... explicit_user_intent') but adds nothing about order_id or response_format. With low schema coverage, the description fails to compensate for the undocumented parameters, leaving the agent to infer order_id and response_format meaning.

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?

The name 'rappi_cancel_order' and title 'Cancel Rappi order' clearly indicate verb+resource. The description adds 'May refund' which gives a hint of the effect, but doesn't explicitly state 'Cancels an order' — it's implied. It distinguishes from read-only order tools like get_order and track_order.

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 description gives preconditions ('Requires mutations and explicit_user_intent', 'Guest tokens rejected') but does not explicitly say when to use this tool vs alternatives. Since cancellation is unique among siblings, the context is clear from the name, but the description lacks explicit 'use when' guidance or exclusions.

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