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

Goes well beyond the annotations: declares the required scope (reservations:write), the risk tier (consequential), the side effects (status update plus an activity log entry), the approval workflow with preview, and a concrete business rule (check-out blocked when a balance is due). It even discloses current unavailability, which prevents a doomed call entirely. Annotations only flag it as non-read-only and destructive; the description supplies the operational context.

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-loads the operation and its rules in the first two sentences, then uses a compact metadata line for scope/risk/effects/availability. A slight redundancy between 'Exige aprovação' and 'prévia + aprovação do usuário obrigatória', but near-zero wasted text overall.

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 consequential mutation with no output schema, it covers the essentials an agent needs: approval flow, refusal condition, side effects, permission scope, and availability. The main gap is the meaning/format of the id parameter and what the success payload looks like beyond 'atualiza o status'.

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 50%: approval_id and idempotency_key are documented in the schema, but id and action are not. The description compensates by spelling out the approval requirement and by giving human-readable labels for each enum value, which clarifies action semantics. It says nothing about id (the reservation identifier), leaving half the parameters underspecified.

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 ('Aplica uma transição de status') and enumerates all seven transitions in Portuguese, mapping semantically onto the action enum. It is distinguishable from siblings like change_reservation_dates or update_reservation_notes, though it never explicitly names cancel_reservation as the alternative for cancellations (only implies it by omitting 'cancel' from the list).

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?

Gives clear preconditions: approval is mandatory, a preview must be obtained first, and check-out with an outstanding balance is refused. The 'INDISPONÍVEL nesta autorização' note tells the agent the tool cannot be invoked at all under the current scope, which is exactly the kind of usage gating an agent needs. It stops short of naming sibling tools for adjacent operations (cancel, date/room changes).

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