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

With no annotations, the description carries real behavioral weight: it discloses that INSS and IRRF are applied on taxable verbas, that historical competência tables are honored via reference_date, that avos are capped at 12, and that aviso trabalhado suppresses the indenizado amount. It does not state the return shape or that the tool is a side-effect-free pure calculation, which is the remaining transparency gap.

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?

Three dense but purposeful sentences, front-loaded with what is computed before moving to parameter mechanics. Nothing is repetitive, though the inclusion list and parameter inventory pack a lot into one block and the naming directive sits mid-paragraph rather than in a distinct slot.

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 10-parameter domain tool with no output schema, the description thoroughly covers inputs and domain scope but never describes the return value's shape or fields, so an agent cannot fully anticipate the response. The input side is complete; the output side is left implicit.

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 already 100%, so baseline is 3, but the description adds value beyond the schema: it groups required (salary, months_worked, type) vs optional parameters and explicitly instructs the agent to use the English parameter names verbatim, which prevents Portuguese-name errors. It adds orientation without duplicating meaning the schema lacks.

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?

States a specific verb and resource (calculate CLT severance) and enumerates the five covered termination types plus the exact monetary components it produces (saldo de salário, férias, 13º, aviso prévio, multa FGTS, INSS/IRRF). This scope listing is enough for an agent to separate it from siblings like calculate_custo_demissao or calculate_aviso_previo without opening any schema.

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?

Gives clear applicability (without_cause, resignation, mutual agreement, with_cause, fixed-term/experience end) and an explicit exclusion ('a saída antes do prazo não é coberta'). It never names an alternative tool to use in the excluded case, so no alternative routing is provided — clear context but no alternatives.

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