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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds substantial behavioral context beyond that: null fields mean absence of information in the source, not a defect; zero results do not prove non-existence and are often due to vocabulary or over-narrow filters; and full texts are accessible via jurisprudencia_documento. These are exactly the kind of non-obvious behaviors an agent needs to interpret results correctly.

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 a single dense paragraph with no filler; every sentence adds information. It front-loads the main purpose and return structure before caveats. It is slightly long but each clause earns its place, so it remains appropriately sized and structured.

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?

For a tool with seven parameters and no output schema, the description covers a lot: return fields, full-text access, null semantics, broad-search behavior, and zero-result interpretation. Missing explanations for date ranges, 'tipo', and 'max' are the main gaps, but the most critical usage contexts are addressed.

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 carries the burden of explaining parameters. It explains 'termo' ('por termo ou tese') and 'tribunais' ('para restringir a busca; sem isso a pesquisa é ampla'), but it does not explain 'tipo', 'data_de', 'data_ate', 'ordenar', or 'max'. An agent would have to guess their meanings or formats, which is a significant gap given the parameter count.

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 clear verb and resource: 'Busca jurisprudência (acórdãos, súmulas, orientações jurisprudenciais, temas) por termo ou tese.' It lists what each returned record contains and explicitly distinguishes itself from jurisprudencia_documento by explaining that full texts are read through that sibling. This gives an agent a precise understanding of what the tool does and how it differs from related tools.

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 tells the agent when to use jurisprudencia_documento instead: when a record has 'texto_integral_disponivel: true'. It also advises to inform 'tribunais' to narrow the search and warns that an unfiltered search is broad. It does not explicitly contrast with jurisprudencia_sumulas, but the main routing guidance is present.

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