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

Goes well beyond the annotations by disclosing billing semantics (same credit holder reopening the same company on the same Brasília day is not charged), failure behavior (503 with no charge and no stale-record fallback), and an interpretation warning ('Missing checks are not a clean result'). These are exactly the operational facts an agent needs and none are derivable from readOnlyHint=false / idempotentHint=false.

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 core distinction and the cnia_atual tradeoff are front-loaded, and every sentence carries operational content. It is somewhat long and drifts into referencing an HTTP path inside a tool description, which is slightly awkward but not wasteful.

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 no output schema, the description usefully tells the agent which response fields matter (dossie.dados, dossie.semaforo.alertas, dossie.semaforo.sem_conferencia) and warns about the meaning of missing checks. The concrete response shape is still unspecified, but the behavioral coverage is high overall.

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 100%, so the baseline is 3, but the description adds real meaning to cnia_atual: what it forces, what happens on failure, and the alternative of inspecting the returned CNIA date instead. It also names which returned fields to read, giving the parameters downstream purpose.

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 opening sentence names a concrete resource (company dossier) and its distinguishing contents (unmasked details, risk signals), which separates it from plain lookup siblings like consulta_cnpj or get_cnpj. It does not, however, explicitly name which sibling to use instead, leaving the agent to infer the distinction.

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?

It gives situational guidance for the flag ('set cnia_atual=true to require a CNIA source check') and a cost-check precondition ('Read GET /api/dossie/preco before spending'), plus a scope caveat ('screening aid, not an official certificate'). It never states when to prefer this over consulta_cnpj, reveal_cnpj, or avaliar, so sibling selection is left implicit.

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