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

The description goes beyond the readOnlyHint annotation by explaining the estimate is based on public average parameters (interest rate, term, down payment) and explicitly states limitations: 'NAO substitui analise de correspondente bancario autorizado pelo Banco Central do Brasil'. This adds behavioral context about what the tool does not do, which is not present in annotations.

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 front-loaded with the main purpose and then lists limitations. It includes both Portuguese and English versions, which is redundant but not excessively verbose. The structure is clear, though the EN summary repeats the same content, adding length without new information.

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 tool with 14 parameters and no output schema, the description is only partially complete. It explains the output is a min-max range but does not specify the return format, units, or how parameters influence the calculation. It also does not address edge cases or required parameter semantics. The educational and non-binding context is useful, but more detail on output and parameter interactions is needed.

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?

With schema description coverage at only 36%, the description needs to compensate, but it only mentions 'taxa de juros media divulgada, prazo informado, entrada informada'. It does not explain the many other parameters like cidade, estado, dependentes, tipo_imovel, sistema_amortizacao, or modalidade_indexador. The description adds minimal meaning beyond the schema, leaving most parameters underspecified.

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 clearly states the tool 'Apresenta uma estimativa educacional, em intervalo (minimo e maximo), do valor de parcela mensal de referencia pra um imovel residencial no Brasil'. This specifies the verb (apresenta), the resource (monthly payment range for a residential property), and the scope (Brazil). It also distinguishes from sibling tools by clarifying it is an estimator, not a search/scheduling tool.

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 when-not-to-use guidance: 'Nao e cotacao, nao e pre-aprovacao, nao consulta bureau de credito, nao classifica em programa habitacional'. This tells the agent this tool is only for educational estimates, not for actual quotes or pre-approvals. However, it does not explicitly name alternative tools to use instead, so it lacks a full 'use X instead' instruction.

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