Criar vários cálculos (lote: um por reclamante ou por devedor)

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

Annotations already declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description is not carrying that burden. It adds genuinely useful behavior instead: every item passes the same gates (documents, map, title, approval), and one item's error does not abort the rest — critical for a batch tool. It stops short of disclosing rate limits, ordering guarantees, or whether partial results are rolled back.

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?

Three sentences, front-loaded with the core action before the use cases and the return semantics. Dense with parentheticals but each clause carries information the agent needs; nothing is padding.

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, the description quite properly covers the return shape (per-item calculation number, state, totals, failures, plus consolidated gross/net totals of settled items). Combined with the error-isolation note and the parallel gates, this is close to complete for a 5-parameter batch tool; only the source of specifications (especificacoes vs arquivos_json) is left entirely to 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 description coverage is 100%, so the schema already explains liquidar_em, arquivos_json, especificacoes, ignorar_tabelas and atualizar_tabelas. The description nods to the list of specifications and the per-debtor period but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 in the batch domain: it runs calculo_criar for every specification in a list, and explicitly distinguishes itself from the single-item sibling by naming it. The parenthetical use cases (litisconsórcio ativo, responsabilidade subsidiária/sucessiva, cenários) tell an agent exactly what "batch" means here.

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?

The scenarios enumerated (one per claimant, one per debtor, multiple scenarios) make the trigger condition clear and imply that a single calculation should go through calculo_criar instead. There is no explicit when-not-to-use statement, but the routing context is strong enough that an agent can choose correctly.

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