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

Since annotations are absent, the description carries the full burden, and it delivers: it explains the reconstructed base, informed vs expected comparison, step-by-step derivation, legal norm and official source, the R$0.10 rounding tolerance, and the explicit refusal behavior. An agent gets a realistic model of what the tool does and when it will or will not produce a result.

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 dense but organized: purpose, coverage scope, computation, tolerance, refusal, and parameter list all appear in logical order. The parameter restatement at the end is helpful but slightly redundant with the schema.

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?

Even without an output schema, the description explains what the tool returns: the difference plus step-by-step derivation, norm, and official source. It also covers important edge cases and behavioral boundaries, so an agent has enough context to invoke it correctly and interpret results.

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. The description only restates which parameters are required/optional and instructs the caller to use exact English names; it does not add semantic meaning beyond the schema's descriptions.

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 opens with a specific verb and resource: 'Confere se o IRRF retido de um empregado CLT bate com o esperado pela tabela vigente'. This immediately identifies the tool as an audit/verification tool rather than a generic calculator, distinguishing it from siblings like calculate_net_salary or simulate_income_tax.

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 states the intended context clearly: checking IRRF for CLT employees against the applicable table. It also gives an explicit when-not condition: if alimony or other deductions are present, the tool refuses rather than producing a false comparison. It does not name alternative sibling tools, so it falls short of full routing guidance.

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