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

Annotations already declare destructiveHint and idempotentHint, so the safety profile is covered; the description adds genuinely new behavior: wallet refund on paid orders and the TEST- order special case. It doesn't say what a refused cancellation returns (error vs. silent no-op), which is the remaining gap for a destructive tool.

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, front-loaded with the core action and precondition, with zero filler. The final sentence about TEST- orders is slightly tacked on but still carries information.

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 one-parameter destructive mutation with no output schema, the description covers the action, the gating conditions, the financial side effect, and a special id case. Only failure-mode behavior is left unstated.

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?

With 100% schema description coverage on the single order_id parameter, the schema already explains the id format. The mention of TEST-... orders in the description reinforces but does not extend the parameter's 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 description uses a specific verb and resource ('Cancels an order') and immediately scopes it with a state precondition ('not in production yet'), which no sibling tool (get_order, create_order, list_orders) shares. It doesn't explicitly contrast itself with siblings, but the unique destructive verb makes the distinction obvious.

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?

It states both the eligible condition (not in production, whether paid or unpaid) and the ineligible ones (in production, shipped), which is exactly the when/when-not guidance an agent needs before a destructive call. It stops short of naming an alternative course of action when cancellation is refused.

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