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

Annotations already establish read-only, idempotent, and non-destructive behavior, so the bar is lower. The description adds valuable behavioral detail by disclosing INSS/IRRF deductions using 2026 tables and the exemption of indemnity-only amounts, which an agent would not otherwise know. It does not contradict the 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?

Two tight sentences front-load the scope and then add the tax-exemption nuance; there is no filler or repetition. It packs many components efficiently without becoming unwieldy.

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 gives a good high-level model of the calculation and its expected outputs, but with nine parameters, two enums, and no output schema, an agent will still be guessing about how motivo changes the calculation and what projetar_aviso and saldo_fgts mean. This is adequate but has clear gaps, so a 3 is appropriate.

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; it names several calculation components that map onto inputs such as salario, aviso, ferias_vencidas, and saldo_fgts. However, it never explains the key motivo enum or optional parameters like projetar_aviso and dependentes, and it does not clarify how the 40%/20% FGTS penalty relates to motivo. Thus it only partially compensates for the schema's silence.

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 identifies the tool as the CLT termination-payout calculation, enumerating concrete components such as salary balance, prior-notice indemnity, proportional 13th, vacation, FGTS penalty, and INSS/IRRF deductions. It is far more specific than a tautology and can be distinguished from siblings like calculo_fgts or calculo_revisional, though it never names an alternative. Because it lacks an explicit verb and direct sibling differentiation, it falls just short of a 5.

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 domain label 'Verbas rescisórias / liquidação trabalhista (CLT)' gives clear context for when the tool is appropriate: computing Brazilian labor severance payouts. It does not state when not to use it or mention alternative tools, such as using calculo_fgts for standalone FGTS calculations. This is clear context without exclusions, matching a 4.

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