Cancel a Zé order (gated)

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

Annotations already declare the tool as destructive, non-idempotent, and not read-only; the description adds genuinely new context: fail-closed error semantics, the ZE_ALLOW_MUTATIONS entitlement check, and a guest-token restriction on charging. This goes beyond what readOnlyHint/destructiveHint convey, though it stops short of describing post-cancellation side effects or response behavior.

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?

Three short sentences with zero filler, front-loaded with the most important trait ('Fail-closed'). Each clause earns its place: error behavior, the mutation-and-intent gates, and the guest-token restriction.

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 low-complexity destructive tool, the description plus annotations cover the core invocation decision: preconditions, required parameter, format choice, and safety profile. The remaining gaps are the response content (no output schema exists) and the provenance/format of order_id, so it is strong but not fully self-sufficient.

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 coverage is low (33%), so the description must compensate; it adds meaning for explicit_user_intent by naming it as a mandatory gate, and response_format is self-documenting via its enum/default. However, the required order_id receives no semantic guidance beyond minLength — no source, format, or provenance hint — leaving the most critical parameter under-explained.

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 title states the exact verb+resource ('Cancel a Zé order') and the '(gated)' qualifier signals the consent-gating behavior. This clearly distinguishes it from siblings like ze_place_order, ze_track_order, and ze_order_history, and the description's fail-closed framing reinforces the action's safety-sensitive nature.

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 concrete preconditions for a successful call — ZE_ALLOW_MUTATIONS must be enabled and explicit_user_intent must be true — which tells an agent when it is appropriate to invoke this tool. It also implies an exclusion ('Guest tokens cannot charge'), but it never names an alternative tool or explicitly says when not to use it beyond that constraint.

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