comparar_anexos

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

With no annotations provided, the description carries the full disclosure burden and does so thoroughly: it reveals the calculation basis (total load vs DAS rate), the folha dependency and its exact mechanism (only Annex IV; 20% employer contribution plus 1%-3% RAT adjusted by FAP), and the misleading result when folha is omitted. It also sets expectations that it computes legal tables and does not address classification.

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 long (six sentences) but each sentence earns its place: load-vs-rate distinction up front, then the folha caveat, sibling routing, scope limits, and disclaimer. It is front-loaded with the core purpose, though it could be tightened slightly without losing the essential caveats.

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 5-parameter tool with no annotations and 0% schema coverage, the description covers purpose, the critical parameter trap, sibling differentiation, and scope limits; the output schema covers return values. The remaining gap is the absence of any prose meaning or constraints for the two required inputs, rbt12 and receita_do_mes.

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 0%, so the description must compensate. It explains folha well (only affects Annex IV, employer contribution at 20%, RAT/FAP mechanics) and indirectly clarifies fap and rat_pct, but the two required parameters, rbt12 and receita_do_mes, receive no prose explanation and rely on self-evident names. Compensation is partial, not complete.

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 first sentence states a specific verb and resource: compares the five annexes by TOTAL LOAD rather than by DAS rate. It explicitly differentiates from the sibling calcular_das ('use this tool, not repeated calcular_das') whenever the question is which annex costs least, so an agent can select it without opening the schema.

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?

Gives an explicit when-to-use rule ('quando a pergunta for qual anexo custa menos') and a when-not-to (not repeated calcular_das), plus the condition to pass folha so the comparison is not misleading. It also states what the tool does not do — it compares costs, does not define annex classification, and is not tax advisory — which prevents off-scope use.

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