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

Annotations already declare the operation is read-only, idempotent, and non-destructive. The description adds meaningful behavioral detail by explaining the computation process: applying percentage factors, discounting remission (work/study) and pretrial detention, and returning a progression date. This goes beyond what the annotations alone convey and clarifies the tool's internal logic.

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 a single dense sentence that front-loads the core subject and legal basis, then packs the mathematical and legal factors efficiently. Every clause adds useful information, and there is no repetition or filler.

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 complex legal calculator, the description covers the main factors and return value well. It names the applicable law, the calculation dimensions, the deductions, and the output. The main gaps are the absence of explicit references to the required sentence length and start date parameters, and the lack of percentage values—though these are likely legal rules rather than tool-specific knowledge.

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?

The input schema has 0% description coverage, so the description carries the burden of explaining parameters. It does map several parameters implicitly: reincidente, hediondo, violencia, resultado_morte, horas_estudo, and dias_trabalhados relate to the named factors. However, it does not explicitly explain the two required parameters (pena_anos and inicio_cumprimento), date formats, or units, leaving partial ambiguity for a complete invocation.

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's purpose: calculating prison regime progression (progressão de regime) and returning the progression date. It names a specific legal basis (LEP art. 112, Lei 13.964/2019) and enumerates the key factors involved, which distinguishes it from sibling calculation tools like calculo_dosimetria or calculo_trabalhista.

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 makes the applicable scenario obvious: computing regime progression for prisoners based on legal criteria such as reincidence, heinous crime, violence, and death result. It does not explicitly name alternative tools or exclusion conditions, but the legal context and factor list are clear enough for an agent to select this tool over the sibling calculators.

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