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

With no annotations, the description carries the full burden, and it does disclose the important financial outcome: nothing is charged and the card authorisation is released. However, it omits permission/auth requirements, whether the cancellation is reversible, whether it is idempotent, and what state the order ends in.

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, front-loaded sentences with no filler; the actor and condition come first and the consequence second. It is efficient, though arguably terse enough that key details were trimmed rather than omitted deliberately.

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 mutation with no annotations and no output schema, the description covers the actor, the precondition, and the financial side effect, which is the essential context. It still leaves the post-call order state and permission requirements 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?

Schema description coverage is 0% for the single parameter order_id, and the description never mentions it or its expected format. 'an order' only weakly implies an identifier; the description does not compensate for the schema 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+resource ('cancel an order') plus a scoping qualifier ('that was not delivered') and an actor role ('Buyer'). It is clearly distinguishable from read siblings like get_order and my_orders, though it does not name any alternative tool explicitly.

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 phrase 'an order that was not delivered' implies the applicable condition, and 'Buyer:' implies the permitted actor, but there is no explicit statement of when not to use it (e.g. delivered orders) and no alternative named (redeliver, get_order). Usage is inferable rather than stated.

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