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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description is consistent with this read-only nature. The description adds meaningful context beyond annotations: no platform credentials required, prepaid per-query pricing model, non-confidential data provenance, and LGPD data controller responsibilities. This gives an agent a realistic understanding of side effects (payment deduction) and compliance expectations.

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?

Four information-dense sentences in a single paragraph, front-loaded with the core purpose before adding payment, data provenance, and compliance details. No filler words. It could be slightly restructured so the LGPD sentence is more integrated, but overall every clause earns its place.

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 query tool with 3 optional parameters and no output schema, the description should clarify what the response looks like (e.g., certificate PDF, JSON with debt status, error on found debts) and whether any identifier is required. The description covers 'where,' 'how,' and 'legal what' but omits the critical 'what do I get back' since neither the schema nor annotations provide this context.

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 coverage is 0% and the description provides zero additional detail about the three parameters (cpf, cnpj, inscricao_municipal). It doesn't clarify that at least one is likely needed, whether they're mutually exclusive, format requirements (with/without punctuation), or which to provide for which use case. The parameter names are self-evident to Brazilian audiences but an AI agent would benefit from constraints like 'provide at least one' or 'inscricao_municipal applies only to Guarulhos-registered entities.'

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 purpose: querying a 'Certidão Negativa de Débitos Mobiliários' (Negative Certificate of Municipal Debts) from Prefeitura SP Guarulhos via official sources. The verb 'consulta' (query) and resource 'CNDM' are specific and identifiable. It's not a tautology, though it could more explicitly differentiate from potential sibling data 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 provides context about when to use the tool: it's a pay-per-query service using prepaid credit, hosted on the platform, and queries public/official data available to citizens. However, it doesn't explicitly state when NOT to use it or name alternatives beyond the payment model. The LGPD note about the client being the data controller is a useful decision factor but isn't a substitute for explicit exclusion criteria.

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