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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description goes well beyond by adding crucial behavioral and legal details: no credentials needed, pay-per-query with prepaid credit, data is public and not confidential, and the client is the LGPD data controller. These details are not present in the structured fields and meaningfully define the tool's behavior.

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 block of text mixing purpose, billing, legal, and compliance information. While it is front-loaded with the main purpose, the legal and administrative details make it longer than necessary. Some redundancy ('Hospedado pela plataforma, sem credenciais da plataforma') could be tightened. It is acceptable but not a model of conciseness.

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 read-only tool with one parameter and no output schema, the description covers key aspects: data source, authentication model, cost, data classification, and LGPD obligations. It is sufficiently complete for an agent to understand the operational context, although it does not specify the response format or potential error conditions, which are not expected given the presence of output schemas.

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?

The input schema defines one required string parameter 'cnpj', but the description provides zero additional information about it. Schema description coverage is 0%, and the description does not mention CNPJ, its format, or usage examples. Since the parameter is the only input and it is not explained, the description fails to compensate for the sparse schema.

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 clearly states the tool queries 'Instalações do SIMP' from official Brazilian sources ('consulta em fonte oficial', 'Consulta informação de fontes e órgãos oficiais brasileiros'). The verb 'consulta' plus the specific resource (ANP installations) makes the purpose clear and differentiates it from sibling tools like 'connect' or 'authenticate'. However, 'Instalações do SIMP' is not elaborated, and some ambiguity remains about the exact entity type.

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 provides operational context (hosted, no platform credentials, prepaid billing) but gives no explicit guidance on when to use this tool over alternatives. It does not mention any 'when to use' or 'instead of' scenarios, and the sibling tools are not referenced. Only implicit context suggests it is for read-only queries.

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