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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds what content is returned (stages, pendências, blocks), which is useful, but says nothing about empty-state behavior or ordering of the returned questions.

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?

A single front-loaded sentence plus one action sentence — no filler. The telegraphic style ('e bloqueios.') is slightly terse but still parseable.

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 no output schema, the description must convey the payload, and it names the three kinds of content an agent will receive. Minor gap: it doesn't say what an empty result means (onboarding complete / nothing pending), which matters for a pendências-style tool.

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?

The tool takes zero parameters, so there is nothing for the description to compensate for; baseline 4 applies. The description correctly implies a parameterless consultation by describing only returned content.

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 enumerates what the tool surfaces — onboarding stages, fiscal questions the cadastro can't answer (Simples rate, apuração regime), and blocks — which is specific enough to distinguish it from siblings like status or minha_empresa. It lacks an explicit verb (list/retrieve), so the read nature is only implied by the noun phrase and the annotations.

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?

It explicitly routes the agent to the alternative: 'Responda com responder_perguntas_fiscais', clearly separating consultation from answering. It does not state when this tool should not be called (e.g., no pending questions) or any prerequisites, keeping it short of a 5.

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