propor_lancar_conta

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

Adds real behavior beyond the annotations: the tool produces display text rather than committing the entry, and confirmation is a separate human-in-the-loop step. There is mild tension with readOnlyHint=false ('NAO lanca nada' reads as no-op, but the call presumably persists a proposal), though this is a staged-write pattern rather than a contradiction. It does not explain whether repeated calls overwrite a prior proposal, which matters given idempotentHint=true.

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 sentences, zero filler, with the most dangerous misconception ('does it actually create the account?') negated up front via capitalization. The next-step instruction follows immediately in reading order.

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?

With no output schema and eight parameters, the description focuses on the highest-risk aspect – that this is a staging step requiring confirmation – which is the right allocation of space. It leaves minor gaps on default behaviors (e.g. data_vencimento defaulting to today) and on what the returned text looks like, but those are recoverable from the schema.

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 63% and five of eight parameters carry inline descriptions, including the audit-critical 'mensagem_do_cliente' rule about literal quoting. The description itself adds no parameter guidance, so the baseline 3 applies – it neither compensates for nor worsens the remaining undocumented fields (tipo, descricao, id_conta_financeira).

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 ('Prepara o lancamento de uma conta a pagar ou a receber') plus the concrete deliverable ('devolve o texto para MOSTRAR ao cliente'). The closing sentence distinguishes it sharply from the sibling confirmar_acao, so an agent can separate the two-step flow without opening either 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?

Gives an explicit negative constraint ('NAO lanca nada') and the exact condition and tool that follows ('so depois que o cliente confirmar e que se chama confirmar_acao'). This is a when-to-use-and-when-not in two lines; the only unaddressed edge is when to prefer propor_dar_baixa or propor_criar_cliente, which target clearly different resources.

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