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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context such as per-deposit processing, 3% a.a. interest, and the current limitation to manual deposits ('Aceita depósitos manuais'), but it does not disclose output format, error conditions, or other limitations.

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 efficiently front-loaded: the first sentence captures the resource, calculation, and interest rate, and the second adds the input mode. The parenthetical future OCR note is a minor non-essential detail, but not distracting enough to be a serious flaw.

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 4-parameter tool with no output schema and no property descriptions, the description gives a solid high-level overview but omits critical invocation details such as the meaning/format of data_calculo, the format of competencia, and the default/enum behavior of indice. The read-only and idempotent annotations reduce some burden, but the agent still cannot fully infer the required call structure.

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 partially compensates: it maps 'índice de inflação' and 'TR' to the indice parameter, directly references depositos, and the 'juros de 3% a.a.' phrase clarifies incluir_juros_3aa. However, data_calculo is never mentioned, and the exact format of competencia or the default behavior of indice are not addressed.

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 states a specific verb and resource: 'Correção do FGTS' with 'por depósito calcula a diferença entre corrigir pelo índice de inflação vs pela TR'. It names the exact legal thesis (TR → INPC/IPCA-E, STF) and clearly distinguishes this tool from the sibling calculo_* 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 implies the usage scenario — correcting FGTS deposits against inflation indices vs TR — but never explicitly contrasts it with alternatives like calculo_revisional or calculo_trabalhista. There is no when-to-use/when-not-to-use guidance, leaving routing to inference.

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