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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond this: it sums corrected installments, is restricted to specific codes, and is framed as an administrative rather than judicial remedy. There is no contradiction with 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 two concise, information-dense sentences. It front-loads the core function and scope, then adds the legal context. No word is wasted.

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 the main purpose, applicable codes, and legal framework, but it does not explain the correction index parameter or calculation date, and there is no output schema to clarify the return value. For a 3-parameter tool with no parameter descriptions, this is adequate but incomplete.

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 must compensate. It partially explains descontos as the discounted installments to be summed and hints at valid codes, but it does not explain the 'indice' parameter's role in correction or what 'data_calculo' means. This is a meaningful gap given the lack of schema descriptions.

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 a specific function: calculating restitution of undue INSS discounts by summing corrected installments. It further narrows scope with specific codes (280/304/310/378) and the STF agreement context, making it distinguishable from sibling tools like calculo_revisional or calculo_fgts.

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 for when to use the tool: cases of undue INSS discounts from associative fraud with the listed codes, under the administrative reimbursement route via the STF agreement. It does not explicitly name alternative tools or give when-not-to-use guidance, so it falls short of a 5.

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