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

With no annotations present, the description carries the full behavioral burden. It discloses key calculation rules: INSS of 11% limited to the monthly ceiling, IRRF via the progressive table, ISS per municipality, a 20% employer contribution, and the effect of other_monthly_base on the INSS ceiling. It also explains that reference_date switches to the tables of that date. It does not cover return-value shape or rounding behavior, but the disclosed rules are substantive.

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The description is compact and front-loads the core calculation components in the first sentence, followed by the historical reference feature and parameter listing. Each sentence earns its place, though the required/optional list slightly overlaps with the schema. Overall it is efficient and well-ordered.

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?

Given five parameters, a tax calculation, and no output schema, the description explains the calculation logic, parameter purposes, and historical behavior sufficiently for correct invocation. It does not describe the response format, which would be useful, but that absence is mitigated by the tool being a calculator and the rich parameter descriptions in the schema.

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 schema already explains every parameter. The description adds value by explicitly listing required versus optional parameters and instructing the agent to use exact English names, which is useful because the description is in Portuguese. It does not add materially new semantics beyond the schema for the parameter effects.

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 the specific verb 'Calcula' and the resource 'retenções do RPA', then enumerates exactly what is computed: INSS, IRRF, ISS, net amount, and total company cost. This scope clearly differentiates it from siblings like calculate_inss_autonomo and check_irrf_deduction by covering the whole RPA calculation rather than a single component.

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 provides clear context by naming the full RPA calculation as the tool's domain, so an agent can infer this is the right choice when a complete RPA receipt is needed. It also highlights a specific use case (reprocessing old receipts via reference_date). However, it does not explicitly contrast with alternatives or state when not to use it, such as when only the INSS portion is needed.

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