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

Annotation already declares readOnlyHint=true/openWorldHint=false/destructiveHint=false, and the description reinforces with 'Não busca nem compra nada'. It adds behavior beyond annotations: two distinct modes (ficha vs. teor read), continuation via paginaTeor when temMais=true, DJEN as a free source for the teor, and the null case for segredoDeJustica. Minor gap: it doesn't say how the ficha is assembled or anything about response size/cost for a large record.

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?

Front-loaded with the core value proposition and then a second mode, with zero filler sentences. It is dense and slightly long, and the 'Não busca nem compra nada' clause is a bit odd, but every other clause carries operational information.

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 still enumerates both possible result sets (ficha fields and teor fields: fonte, data, situação, republicações, correspondência exata ou temporal), documents the pagination signal (temMais), the unknown-secrecy case, and the exit path for other pages. Nothing an agent needs to call it correctly is missing.

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, but the description adds real semantics: teorEventoId is sourced from linha_do_tempo/ultimas_movimentacoes and switches the whole return shape, and paginaTeor is a continuation cursor valid only when temMais=true. This is meaning the schema alone does not convey.

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?

Opens with a specific verb+resource ('A FICHA COMPLETA de um processo em UMA leitura') and then enumerates exactly what the record contains: CNJ metadata, parties with polo and counsel, deadlines, next hearing, latest movements, case-file coverage. It explicitly positions itself against five named siblings (buscar_processos, listar_pecas, listar_prazos, ultimas_movimentacoes, linha_do_tempo), so an agent can distinguish it 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 explicit ordering guidance ('Use ANTES de navegar nos autos') and states the tool replaces a known choreography of five calls. It also routes the alternative case ('Para outras páginas use buscar_autos/ler_paginas') and explains the second mode's entry point (teorEventoId from linha_do_tempo or ultimas_movimentacoes). When-to-use, when-to-use-something-else, and the mode switch are all covered.

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