Criar cálculo completo no PJe-Calc

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

With annotations only declaring readOnly=false/idempotent=false/destructive=false/openWorld=true, the description carries the real behavioral burden and delivers: side effects (starts PJe-Calc, imports, regenerates ocorrências, writes -PRONTO.PJC/-LIQUIDADO.PJC/-RELATORIO.pdf), a documented state machine ('estado': rascunho, aceito_pelo_aplicativo, calculado, simulacao, auditado), gate conditions ('bloqueiosDeEntrega'), and the caveat that delivery review is always human. That is substantive disclosure beyond the annotations.

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?

It is front-loaded with the recommended-flow statement, but the body is a very long, run-on, jargon-heavy sentence with three dense clauses about liquidation, returns, and data-contract gating. Almost every clause carries real information, yet the wall-of-text structure makes it hard to scan.

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 high-complexity orchestration tool with no output schema and a nested free-form especificacao object, the description supplies what an agent needs: the full execution sequence, the returned fields and state values, the produced artifacts, the blocking/precondition rules, and the delimiter of automatic vs. human responsibility.

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 schema already explains every parameter (destino, iniciar, liquidar_em, exportar_final, ignorar_tabelas, atualizar_tabelas, etc.), making 3 the baseline. The description adds only a little param-linked meaning, mainly that liquidar_em triggers a TEST liquidation and the downstream verification set; it does not clarify the especificacao object contract beyond pointing at calculo_modelo_json.

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?

The description states a specific composite action ('Fluxo completo e recomendado para montar um cálculo') and enumerates the exact steps performed (validate spec, generate .PJC, import, apurar cartão de ponto, ligar verbas, regerar ocorrências, devolver número). It is unmistakably distinct from atomic siblings like calculo_gerar_pjc or calculo_importar_pjc. It does not, however, name any sibling explicitly to steer the choice, so it stops short of a 5.

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 signals this is the recommended end-to-end flow and specifies conditional behavior: with liquidar_em it also liquidates and verifies; under a data contract it refuses to generate while a mandatory document is missing, auditing failed, or the interpretation plan is unapproved. No explicit 'when NOT to use / use X instead' statement is given against the ladder of single-step siblings.

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