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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description still adds the business rule (time/state window), the exact error code returned on refusal, and the irreversibility fact ('cannot be revived, only re-placed from a new quotation'). This is real behavioral context an agent cannot infer from structured fields.

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 dense sentences plus the endpoint. The WRITE/DESTRUCTIVE label and the cancellation window are both front-loaded, and every clause carries a distinct fact (constraint, error code, irreversibility, route) with no repetition of the title.

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?

No output schema exists, and the description covers what matters for a destructive two-parameter operation: preconditions, failure signal, and post-state irreversibility. Combined with the schema's confirm gate, an agent has everything needed to decide whether to call and to interpret a refusal.

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 100%, so order_id and the confirm:true gate are already fully documented, including the explicit-confirmation requirement. The description only echoes the orderId path parameter and adds nothing about the confirm flag, which is baseline-adequate rather than additive.

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 a delivery order') and immediately qualifies it with the allowed order states. Names the underlying endpoint DELETE /v3/orders/{orderId}, which pins the operation unambiguously against siblings like lalamove_get_order or lalamove_change_driver.

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 an explicit when-it-works condition (ASSIGNING_DRIVER, or <5 minutes after driver acceptance) and the failure mode otherwise (ERR_CANCELLATION_FORBIDDEN), plus the recovery path (re-place from a new quotation). It does not name which sibling to use when the cancellation window has closed, so routing to alternatives is implied rather than stated.

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