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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe and idempotent. The description complements this by adding key behavioral details: the portal is hosted by the platform, requires prepaid credit per query, no platform credentials are needed, and the client is the data controller under LGPD. These disclosures go beyond the annotations and are valuable for an agent to understand the operational context.

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 that front-loads the core purpose and key operational details. Each sentence adds important information: official source, platform hosting, payment model, data type, and LGPD compliance. It is concise with no filler, achieving high information density in limited space.

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?

Given the tool's simplicity (one parameter, no output schema) and thorough annotations (read-only, idempotent, non-destructive), the description provides enough context: it covers majority of relevant aspects—data source, payment, credential requirement, data type, and legal responsibility. It doesn't describe return values, but the output schema is absent and the tool likely returns standard query results, so the description is reasonably complete for the tool's complexity.

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 schema has one required parameter, 'cnpj', which is a string. The description does not mention this parameter at all, and schema description coverage is 0%. However, the parameter is self-explanatory: a CNPJ (Brazilian company registration number). The description could have added context about format or validation, but the name 'cnpj' is quite clear. Given only one parameter and high clarity of name, a baseline score of 3 is appropriate as the description adds minimal value over the 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 purpose: consulting leniency agreements (Acordos de Leniência) from the official transparency portal. It identifies the resource (leniency agreements) and the action (consult/consultar). It distinguishes from siblings by specifying the Brazilian official transparency portal and the type of data (not secret/sigiloso), though it does not explicitly compare to other portal 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 clear context on when to use this tool: to query information from official Brazilian sources, similar to what citizens can access. It implies that it's for legitimate compliance purposes under LGPD. However, it does not explicitly state when NOT to use it or mention alternative tools by name, though the sibling list includes 'marketplace' and 'connect' which might be alternatives.

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