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

The description goes beyond the readOnly/idempotent annotations by disclosing the return payload (per-installment memória de cálculo, totals, premises) and a conditional warning in 'notice' when due dates are missing after the last installment. It also states that partial and late payments are handled, which affects the calculation behavior. No error or rate-limit behavior is described, but the safety profile is already fully covered by 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?

Four dense sentences, front-loaded with the core action and regime scope, followed by accepted input cases and the return shape. The legal citations are heavy but functional; nothing is gratuitous padding.

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?

With 14 required parameters, seven enums and no output schema, the description compensates by describing the output (memória de cálculo, totals, premises, notice), which is otherwise unavailable to the agent. Combined with 93% schema coverage, an agent has what it needs to construct a call, though the routing against overlapping siblings remains unaddressed.

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 93%, so nearly every parameter already carries its own enum/meaning documentation, and the description adds little parameter-level detail beyond the regime list. The baseline of 3 applies: the schema, not the description, does the semantic work.

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 ('Atualiza um débito parcela por parcela') and enumerates the legal regimes it handles (contract, art. 406 CC, labor/TST, Fazenda Pública, art. 523 CPC), so an agent knows exactly what calculation it performs. It does not, however, name or distinguish itself from close siblings such as sentence_execution_calculate or labor_calculate, which overlap with the regimes it lists.

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?

'Aceita pagamentos parciais ou em atraso' plus the regime list gives clear context for when the tool applies, and the per-regime framing signals which inputs select which branches. There are no explicit exclusions or pointers to alternatives, so the agent must infer routing against siblings like sentence_execution_calculate.

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