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

Annotations only give generic hints (readOnlyHint=false, destructiveHint=false), while the description adds real behavioral facts: the operation is reversible, requires no approval, enforces UI-equivalent document validations with actual CPF/CNPJ checking, and creates a Customer plus an activity record. It also discloses the required scope and the current authorization state, which no structured field provides.

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 validation rule is front-loaded in a dense but readable sentence, followed by a compact metadata line covering scope, risk, effects and availability. The scope/risk/effects triple is slightly boilerplate but each token carries decision-relevant information; nothing is redundant.

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 15-parameter mutation with no output schema, the description covers what matters for correct invocation: type-dependent document requirements, reversibility, permission scope, side effects, and current unavailability. It omits what a successful response returns, but with no output schema and low-risk non-destructive semantics that is a minor gap.

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% across 15 parameters, so the description must carry the load; it does explain the critical conditional rule that person/company types require document_type + document_number with CPF/CNPJ validation, which the schema does not encode (only first_name is required). The remaining dozen-plus fields (address, phone, birthday, notes, trade_name) are left unexplained beyond their self-evident names.

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 concrete verb ("Cria") and the exact resource variants it produces (pessoa, empresa, agência), so an agent can immediately tell this is the guest/customer creation tool. It doesn't explicitly contrast itself with update_guest or search_guests, keeping it just short of a 5.

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?

Adds operational context beyond the name: same validations as the UI, reversible, no approval required, and the guest:write scope. Most importantly it flags "INDISPONÍVEL nesta autorização," which directly tells the agent not to attempt the call – a strong, actionable usage signal. It still does not name when to prefer siblings (update_guest, search_guests).

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