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

Annotations only declare destructiveHint=true, so the description carries the rest and does so thoroughly: the four outcome states including which failures are recoverable vs. require account-owner action, the near-duplicate escalation behavior, and the atomic idempotency guarantee against double-charging. This is exactly the extra behavioral context the annotation can't express.

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?

Front-loaded with purpose and return states, then retry semantics — a sensible order with no filler sentences. It is on the long side and the idempotency guidance partially restates the schema's own idempotency_key description, which costs a point.

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?

Nine parameters with no output schema, so the description must explain return values — and it does, enumerating approved/pending_review/denied/failed and the retry-safety contract. Nothing an agent needs to invoke this tool correctly is missing.

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 the baseline is 3, but the description adds operative meaning about idempotency_key that goes beyond its schema text: reuse the same key across retries, fresh key only for a distinct purchase, and that the key is the only fully atomic protection against concurrent double-submits. No added detail on merchant_country_code or amount limits, keeping it below 5.

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 ('Submit a purchase request') and immediately enumerates the possible outcomes. It also implicitly routes the agent by naming check_status as the polling target after a pending_review escalation, which separates it from the read-only siblings (check_status, get_spending_summary, retrieve_card).

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?

Explicitly says when to retry (same idempotency_key on timeout/error), when NOT to retry (duplicate escalation to pending_review — poll check_status instead), and when to use a fresh key (genuinely new purchase). Alternatives and exclusions are both covered.

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