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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=true. The description adds real context: the selection is persisted per owner, can be recovered on other devices by linking the account, and repeating the current selection does not write (reinforcing idempotency). However, it never explains the destructiveHint=true flag — what prior selection state is replaced or lost — which is the most consequential behavior an agent should know.

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 short but wastes space: "não executa análise" appears twice, once at the start and once at the end, and the persistence/linking sentence is a related-feature aside rather than core behavior. Front-loading is fine, but the repetition is avoidable padding.

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 one-parameter tool with no output schema and annotations covering the safety profile, the description is close to adequate, covering persistence and idempotency. The main omission is the destructive behavior implied by destructiveHint=true, which is neither confirmed nor scoped, leaving the agent unable to judge the consequence of re-selecting.

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?

There is a single required parameter (cnpj) and schema description coverage is 100%, with the schema already specifying 14 digits with valid check digits. The description adds no format or validation detail beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ("Seleciona empresa cadastrada") and explicitly excludes an adjacent function ("não executa análise"), which helps separate it from analysis tools like analisar_participacao. It does not, however, distinguish itself from near-siblings such as adicionar_empresa, buscar_empresa or minhas_empresas.

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 the usage context (select a company already registered, persisted for the owner, recoverable across devices when the account is linked) and gives an implicit when-not (this is not the tool for running analysis). It never names an alternative tool or states a selection condition, so routing remains inferred rather than guided.

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