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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds one genuinely useful behavioral fact: the computation is performed by code rather than generated, and results come with legal grounding and stated premises. It does not say what the response contains (which dates, in which format), how invalid or incomplete inputs are handled, or what the null-tolerant params imply.

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 short sentences with no filler, and the scope enumeration is front-loaded. The second sentence earns its place by flagging code-based computation with legal basis. It is compact rather than padded, though the economy contributes to the parameter gap.

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 domain tool this complex — 9 required parameters, a nested penalty object, two enums, no output schema — the description is thin. The heavy lifting is done by the exceptional progressionPercent schema description, but the absence of any return-shape or edge-case statement leaves real holes. It is minimum-viable rather than complete.

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 only 11%: just progressionPercent is documented (and documented very richly, including the LEP fractions and the hediondo caveat). The description contributes no field-level meaning of its own; the mapping from 'remição' to workDays/studyHours/completedEducation, or from 'detração' to detractionDays, is only implicit. With 8 of 9 required parameters carrying no documentation anywhere, the description needed to compensate and does not.

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 names the resource (datas da execução da pena) and enumerates the four outputs computed: progressão de regime, livramento condicional, remição and término. That is enough to distinguish it from most siblings such as criminal_prescription_calculate or dosimetry_calculate. It stops short of explicitly ruling out the closest neighbours, early_termination_calculate ('término') and prazo_calculate, which an agent could plausibly confuse it with.

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?

There is no statement of when to use this tool, when not to, or which sibling to prefer for a related question. The only contextual sentence ('A conta é feita por código, com fundamento e premissas') describes how the result is produced, not when to invoke it. An agent must infer the use case entirely from the title and parameter list.

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