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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description discloses several non-obvious behaviors: null fields mean absence of information in the source, not a defect; zero results don't prove non-existence; and search operators (space, quotes, OR, minus) affect query semantics. This materially helps the agent interpret results and craft better queries.

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?

The description is compact but information-dense, with the core purpose and return fields in the first sentence, followed by logical caveats and usage notes. Every sentence adds value—none repeat the schema or annotations. The flow from purpose to follow-up tool to edge cases to parameters is well organized.

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?

The required parameter `termo` is thoroughly explained, the return shape is described, and edge cases (null fields, zero results) are covered. However, with no output schema and no property descriptions in the input schema, the lack of guidance on optional filters like date range and `tipo` leaves a moderate gap for an agent aiming to build precise queries. Still, the most essential call-time information is present.

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 0%, so the description must compensate. It does a good job for `termo` (full operator syntax) and `tribunais` (scope control), but it leaves `max`, `tipo`, `data_de`, `data_ate`, and `ordenar` unexplained. Since five of seven parameters are only documented by their schema names/types, the compensation is partial and the agent may guess at date formats or allowed `tipo` values.

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 opens with a specific verb and resource: 'Busca jurisprudência (acórdãos, súmulas, orientações jurisprudenciais, temas) por termo ou tese.' It lists the types of content covered and the output fields, making the tool's scope unambiguous. It also implicitly distinguishes itself from the sibling jurisprudencia_documento by noting that full texts are read with that tool, so an agent can tell search from retrieval.

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 description gives clear guidance on when to use jurisprudencia_documento (when `texto_integral_disponivel: true`) and explains the effect of omitting `tribunais` (broad search). It also warns that zero results may indicate vocabulary mismatch or overly narrow filters. However, it does not explicitly address when to prefer sibling jurisprudencia_sumulas, so it stops short of a full when-to-use/alternatives matrix.

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