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

Annotations already cover read-only/idempotent/closed-world, but the description adds real behavioral context beyond them: output varies by credential type (X-Credito vs X-Wallet-Token), balance is shared across Radar CNPJ, PontoFato and EditalMD, and wallet credentials are issued per-portal. That is exactly the kind of auth-dependent behavior an agent needs before deciding to call it.

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?

Two sentences, front-loaded with the returned payload and followed by the credential branching, with no filler. Slightly dense in the second sentence but every clause carries operational meaning.

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 parameters and no output schema, the description carries the burden of saying what comes back, and it does list the four data groups plus the conditional on credentials. Minor gap: it doesn't indicate the shape of the plan/offer data (currency, tiers, whether prices are per-call), though that is largely nameable from the response itself.

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 the baseline is 4; there is nothing for the description to disambiguate. The mention of header-based credentials is useful naming even though no schema properties exist.

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 call returns (free allowance, the single package, the three plans, the balance) and frames it as a 'lookup service', so an agent knows this is a read of pricing/plan/balance data rather than an operation on CNPJ records. The opening phrase 'CNPJ and address lookup service' is slightly confusing since siblings consulta_cnpj/consulta_endereco do the actual lookups, and no sibling is explicitly named to distinguish this from pricing or billing.

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?

Usage is only implied through the credential conditions ('without a credential... with an account...'), which implicitly tells the agent that an anonymous call returns offers and an authenticated call returns balance. There is no explicit 'use this instead of pricing/billing/api_access when...' guidance, so the agent must infer the split among four closely related commercial tools.

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