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

With no annotations, the description carries full disclosure burden. It explains the tax treatment of both PGBL and VGBL, the reinvestment of the restitution, and the regressive-table horizon. It also lists required and optional parameters, but it does not describe what the output looks like (since there is no output schema).

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 a single dense sentence followed by a parameter summary. Every part contributes to understanding the calculation, but the first sentence is a run-on with several clauses, and the parameter guidance could be structured more clearly.

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?

The calculation methodology is well covered, and all parameters are documented in the schema. However, since there is no output schema, the description should ideally state what the tool returns (e.g., final net comparison, recommendation), and this is missing, leaving the agent to guess the result format.

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 baseline is 3. The description adds value by marking which parameters are mandatory vs optional and emphasizing that annual_contribution is equal in both scenarios while gross_annual_income is the basis for the 12% cap, which is not stated explicitly in the schema for the relationship.

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 specific comparison (PGBL vs VGBL) and the concrete mechanism: 12% deductible of taxable income with reinvested restitution, VGBL taxed only on yield, regressive table, redemption after 10 years. This clearly distinguishes it from generic siblings like compare_investments.

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 scenario is clearly established ('pro mesmo aporte anual', 'resgate após 10 anos'), so an agent knows when this applies. However, it does not explicitly state when not to use it or name an alternative tool such as compare_investments, so no exclusion guidance is given.

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