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

With destructiveHint and idempotentHint already declared, the description adds real value: it discloses that the service verifies ownership and per-item fulfillment cutoffs, and that it 'returns actual refund state' rather than a canned acknowledgement. It doesn't restate irreversibility explicitly, but the eligibility/cutoff disclosure is the more useful non-obvious trait.

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?

Four sentences, purpose front-loaded, then the pre/post-payment split, then service guarantees and required inputs. Dense but nearly every clause carries information; only the card_ids repetition of the schema is mildly redundant.

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?

An output schema exists, so return values needn't be explained, and safety annotations cover the destructive/idempotent profile. The remaining gap is the required expected_revision parameter, whose concurrency semantics are not explained anywhere the agent can see them.

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 50%: card_ids and order_access_token are already documented in the schema, and the description largely repeats the card_ids guidance. The two undocumented parameters are only partially addressed — order_id and order_access_token are named as required, but expected_revision is only alluded to as 'at its current revision' with no explanation of optimistic-concurrency failure.

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 an eligible purchase') plus the scoping condition ('at its current revision'), and splits behavior by pre-payment vs post-payment state. An agent immediately understands this mutates an existing order, which no sibling (prepare_order, read_order, search_cards) does.

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 concrete conditional usage: omit card_ids before payment for whole cancellation, supply card_ids after payment for partial cancellation. It does not explicitly name alternatives or state when not to use it (e.g. ineligible/non-cancellable orders), so it stops short of full routing guidance.

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