Update a subaccount

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety bar is partly met; the description goes further with non-obvious behavior — a payout-account change re-runs name enquiry and the new account is only used after a cooldown surfaced via `settlement_account.usable_from`, plus the irreversibility of live-mode changes. The one weak spot is the amount/destination confirmation line, which describes money movement rather than this tool's actual field mutations.

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 the purpose, then the payout-account caveat, then the risk warning — a sensible ordering that an agent can scan. The closing sentence about confirming the exact amount in kobo is inapplicable to this schema and reads as boilerplate that could be trimmed.

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 destructive, non-read-only mutation with no output schema, the description covers what an agent most needs: which fields are changes, the cooldown after a payout-account swap, and that live-mode effects are irreversible. It omits permission/auth requirements and has no return-shape note (there is no output schema), but the critical risk context is present.

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 schema coverage at only 29%, the description must compensate, and it largely does: it names four of the parameters by purpose and explains that `bank_code` only makes sense paired with `account_number` and triggers re-verification. It still does not clarify `status` transitions or `metadata` merge/replace semantics, which are the remaining undocumented parameters.

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 ("Update a subaccount") and immediately enumerates the mutable surface — name, email, status, metadata, and the payout account pairing. That is enough to separate it from create_subaccount, get_subaccount, and list_subaccounts without opening the schema.

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 gives a precondition ("Before calling, confirm the exact amount (in kobo) and the destination with the user") and flags live-mode risk, which is real usage guidance. However, it names no alternative tool and gives no when-not-to-use condition, and the "exact amount (in kobo)" instruction does not map to any parameter on this tool, so the guidance is partly inapplicable.

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