Importar a leitura do AuditorProcessual

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real value beyond that: it enumerates what the returned suggestion object contains (contrato.documentos per peça, contrato.leitura with unreadable pages, processo number, jornadas with converter checks, remunerações, pagamentos, afastamentos) and warns that results are suggestions to be verified page by page. It does not describe behavior on missing folders or malformed files.

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?

Purpose is front-loaded in the first clause, but the body is one long run-on sentence whose enumeration of returned fields is dense and hard to scan as a list of outputs. Every element is informative, yet the packaging costs readability.

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?

There is no output schema, so the description must carry returns, and it does so thoroughly, along with input file semantics, a verification caveat and a documentation reference. The remaining gap is error/edge behavior when folders or optional files are absent.

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 100%, so the baseline is 3. The description does add structure about the pastas content (manifest.json, pages.jsonl, pendências) and what ledger, eventos and revisao represent, but prefixo, processo and numero_processo are never explained, and the file-level semantics largely restate the schema descriptions.

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: reads the output of AuditorProcessual (the ingest_document.py folders plus optional ledger/events/revision files) and returns suggestions for the specification. It clearly distinguishes itself from the other importers in the sibling list (cartoes_para_jornadas, holerites_para_historicos, extrato_para_fgts) by naming the exact source artifact.

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 context of use is implied clearly by the required input (pastas produced by ingest_document.py), and it carries a useful caveat, 'Sugestão não é leitura: confira cada página', plus a docs pointer. However, it never says when not to use it or which sibling to pick instead when the data has a different origin, leaving routing to inference.

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