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

Goes well beyond the annotations: states the password is validated against the portal and never stored or returned, discloses the 3-attempts-per-day lockout risk, the immediate synchronous response, and the downstream effect of reading fiscal registration and pulling 90 days of invoices. This is exactly the context the annotations (readOnlyHint=false, openWorldHint=true) cannot convey.

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?

Front-loaded with what the tool does, then credentials handling, side effects, usage restriction and follow-up — each sentence carries distinct information. Slightly dense in a single paragraph, but nothing is wasted.

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?

No output schema exists, and the description compensates by saying it answers immediately with the attempt result and pointing to situacao_credencial for the asynchronous outcome. For a credential-connecting mutation with a rate-limited external portal, nothing an agent needs to call it safely is missing.

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 coverage is 100%, so the baseline is 3; the description adds real disambiguation by clarifying the password is the Emissor Nacional portal password and 'não é a conta gov.br'. The ciente_ultima_tentativa flag is left entirely to the schema, which is acceptable given its description calls out the situacao_credencial dependency.

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?

Specific verb (conecta) plus resource (empresa da conta ao Emissor Nacional) plus the credentials required. It is clearly distinct from siblings like situacao_credencial or consultar_cnpj, which only read state.

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?

Explicit gate: 'Só use quando a pessoa pedir e informar a senha ela mesma', plus the hard portal rule of at most 3 wrong attempts per day. It also names the follow-up path (situacao_credencial until proximo_passo leaves "aguardar"), so the agent knows both precondition and next step.

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