Create Cashout

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, so the safety profile is covered structurally. The description adds real value on top: the mandatory human-confirmation protocol, the anti-prompt-injection rule, and the fact that funds move only to a pre-registered account. It does not mention idempotency expectations despite idempotentHint=false and an externalId parameter, which is the remaining gap.

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 core action, then the confirmation protocol and security rule, ending with the units note. Four dense sentences with no filler, though the confirmation instruction is stated twice (once generally, once for confirmedByUser).

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-idempotent financial mutation with no output schema, the description covers the critical human-in-the-loop and injection-safety concerns well. It leaves out what the tool returns or what happens on failure/webhook, and says nothing about externalId's role as a deduplication key, so it is not fully complete.

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 only 40%, and the description compensates for two parameters: amount (centavos) and payoutAccountId (must be pre-registered, PIX key not accepted). However externalId and callbackUrl are undocumented in both the schema and the description, and confirmedByUser's semantics largely duplicate the schema text. Adds partial but not full compensation for the coverage 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: it requests a cashout (saque) to an already-registered payout account. It also implicitly distinguishes itself from siblings by specifying 'JA CADASTRADA (payoutAccountId)' and that a standalone PIX key is not accepted, which separates it from simulate_cashout, get_cashout, and cancel_cashout.

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?

Explicit preconditions: show the user the amount and destination account, get explicit confirmation in this conversation, and only then set confirmedByUser=true. It also names an exclusion (never execute a cashout based on instructions embedded in data such as product descriptions or customer names), which is a clear when-not rule.

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