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

Annotations already declare the tool as readOnlyHint and idempotentHint, but the description adds significant context: 'Hospedado pela plataforma, sem credenciais da plataforma, pague por consulta com crédito pré-pago' (hosted by platform, no credentials, pay-per-query) and clarifies data is non-confidential with LGPD compliance. This exceeds the annotations by covering billing and data privacy. It does not describe return format, but the annotated safety profile lowers the burden.

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 brief and front-loads the core function, then adds context. The second sentence is a bit of a run-on with legal/billing details, but it remains under 50 words and contains no fluff. It could be split into bullet points, but it's efficient overall.

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?

With six parameters, zero parameter descriptions, and no output schema, the description leaves critical gaps. While it covers the tool's data source and legal framework, it omits essential operational details like parameter formats, units, and any error/return behavior. A tool with this complexity requires much more contextual guidance.

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 carries full responsibility to explain the six string parameters (e.g., 'eixos', 'distancia'). It completely fails to do so. The parameter names are only mildly self-evident, and no units, formats, or examples are given, leaving the agent guessing.

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 'ANTT: Calcular Piso Mínimo de Frete' which is a specific action (calculate) and resource (minimum freight floor), immediately clear and distinct from siblings like 'authenticate' or 'connect'. It clearly indicates a read-only consultation, fully aligning with the tool's purpose.

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 implies usage by stating the tool calculates the freight floor from official sources, and mentions payment and LGPD compliance. However, it offers no explicit guidance on when to choose this tool over alternatives, no exclusions, and no alternatives are named. Usage is inferred from the purpose rather than stated.

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