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

Goes well beyond the annotations (which only flag it as a non-read-only, non-destructive, non-idempotent write). It discloses partial-failure semantics ('erro em um título NÃO derruba os demais'), the response envelope (`baixas`/`erros`), the 50-item cap, and that `conciliar` is the only API path to reconciliation — exactly the behavioral detail an agent needs.

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?

Dense but front-loaded: purpose first, then the identifier semantics, then the flags and failure mode, then the limit. Every clause adds distinct operational value with no filler.

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?

No output schema exists, yet the description describes the return structure (ok entries with codigo_baixa, plus per-title errors), the batch limit, identifier resolution, and default inheritance. Given the complexity of a batch write tool, this is complete enough to invoke correctly.

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 0% schema description coverage, the description carries the burden and delivers: it explains `codigo_lancamento` (= Omie id, matching codigo_lancamento_omie in get/list), the `codigo_lancamento_integracao` alternative, the item-level vs batch-default semantics of `data` and `conta_corrente`, and the meaning of `conciliar`. It omits the numeric fields (juros, multa, desconto) and codigo_baixa_integracao, so not exhaustive.

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 ('dá baixa em VÁRIAS contas a receber numa chamada') and immediately clarifies the mechanism (LancarRecebimento por título, loop interno). An agent can distinguish this batch tool from the singular omie_settle_receivable and from omie_reconcile_receipt without opening any 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 clear context ('o caminho pra conciliar um mês inteiro contra o extrato do banco sem uma chamada por título') and a conditional rule for `conciliar:true` when the baixa comes from a bank statement. It stops short of explicitly naming the single-title sibling as the alternative for small workloads, leaving that to inference.

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