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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false. The description adds value by noting this is public data available to all citizens ('a mesma disponível ao cidadão, não é dado sigiloso'), clarifying the non-confidential nature, and handles LGPD compliance by stating the client is the data controller. It doesn't contradict annotations and provides reasonable disclosure beyond what annotations offer, though it could have gone deeper on privacy/data retention specifics.

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 focused paragraph of reasonable length (2-3 sentences), providing critical non-obvious information (government data source, LGPD considerations, prepaid consulting model, public nature of data). It's front-loaded with the core purpose. Slightly cryptically worded with the middle 'Hospedado pela plataforma, sem credenciais da plataforma, pague por consulta com crédito pré-pago' but concise overall.

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 simple 5-parameter tool with no output schema and clear annotations, the description essentially covers the essentials: domain (official Brazilian sources), nature of the operation (consult), and legal compliance (controlador LGPD). However, it operates under the assumption that the agent understands how to combine the 5 parameters (width of a national database query), and it would have been strengthened by mentioning the completion or recommendation of the fields, especially since 3 parameters (cpf, cnpj, processo) appear mutually exclusive, and 2 data parameters are required.

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 had the burden to compensate. It mentions the domain (processos, dados de fontes oficiais) and the distinction between person (cpf), company (cnpj), and process (processo) identifiers. However, it doesn't explicitly map parameters to their formats (CNPJ 14-digit, CPF 11-digit, date format for data_inicio/data_fim), the required field combination (data_inicio + data_fim), or clarify whether the combination is a filter versus standalone search criteria. This is a missed opportunity given the 0% coverage.

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 uses a clear verb-resource-scope structure: 'Consulta informação de fontes e órgãos oficiais brasileiros' (consult Brazilian official sources/agencies). It clearly identifies the tool as a read/query operation for processes and specifies the Brazilian public-domain context. However, since sibling descriptions aren't shown, specific sibling differentiation is only partially achievable, keeping it from a 5.

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 clearly implies this is a consult/read operation and explains the revenue model ('pague por consulta com crédito pré-pago'), which tells users about associated costs. However, it doesn't explicitly state when to use this tool versus alternatives, nor does it provide explicit exclusions or alternative tool names. Usage is implied by context rather than explicitly stated.

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