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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses that access is credential-free, payment is via prepaid credits, and the data comes from official public sources. It also adds LGPD compliance context about data controllership, which is useful behavioral and legal-accountability information not captured by annotations.

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 concise and front-loaded with the core purpose. The second and third sentences add operational and legal context that earns their place, but the LGPD sentence could be seen as slightly tangential for tool selection. Overall, there is no fluff and it remains efficient.

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 description covers access type, cost model, and data publicness, providing a reasonable operational picture. However, it omits details about the 'completo' parameter and does not describe the output/return format. Given the absence of an output schema and the low parameter coverage, this leaves notable gaps for an agent using the tool.

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?

With 0% schema description coverage, the description must compensate for parameter documentation, but it only references 'CPF ou CNPJ' as inputs. It does not explain the required presence of both Cpf and Cnpj, nor does it describe the optional 'completo' boolean parameter, leaving users uncertain about its meaning and potential effects.

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 begins with 'Emite a certidão negativa do Ministério Público Federal para uma pessoa ou empresa a partir do CPF ou CNPJ', which clearly states the verb (emite), the resource (certidão negativa do MPF), and the input identifiers (CPF/CNPJ). This distinguishes it from unrelated siblings like authenticate or marketplace.

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 specifies that the tool is hosted on the platform, requires no credentials, and is billed per query using prepaid credits, giving clear operational context. It also notes the data is public and not private, which helps clarify appropriate use. No explicit alternative tool is mentioned, but none of the siblings serve a similar function.

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