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

Annotations already cover readOnlyHint and openWorldHint, so the safety profile is known. The description adds genuinely useful behavior: results carry the real julgado with official source, and the agent is warned never to fabricate citations. No mention of pagination or result limits, which keeps this from a 5.

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 purpose, source scope, and use case before the citation warning and parameter hint. Dense and informative with little waste, though the source enumeration and return-field list make it longer than strictly necessary.

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 correctly compensates by listing the returned fields (ementa, processo, relator, data, link da fonte oficial, escopo coberto). Combined with annotations covering the safety profile and full schema coverage, an agent has everything needed to call and interpret the tool 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?

Schema coverage is 100%, so baseline is 3, but the description adds a conditional usage rule for tribunais (filter only when the user specifies), which is guidance the schema does not provide. Example values are already in the schema, so the marginal gain is modest rather than substantial.

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 (Busca) and resource (decisões judiciais brasileiras reais) with an explicit scope enumeration of sources (27 TJs, 6 TRFs, STF, STJ, TST, TNU) and content types (acórdãos, súmulas, teses, repetitivos). The purpose is unmistakable, but it differentiates itself only from general web search, not from the actual sibling verificar_citacao.

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 ('Útil para encontrar jurisprudência/precedentes que fundamentem uma resposta jurídica') and contrasts with web search, plus a conditional for filtering tribunais when the user specifies. It stops short of naming verificar_citacao as the alternative for validating a known citation, leaving that routing to inference.

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