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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds information they cannot carry: the required scope 'sync:execute', an explicit 'Efeitos: Nenhum' statement, and a hard availability gate based on granted scope or module role. That availability disclosure is behaviorally material and prevents wasted calls.

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 compact blocks: the payload sentence up front, then a metadata line for scope/risk/effects/availability. No filler, and the most decision-relevant fact (it does not start anything) lands early. Slightly dense packing of scope, risk, effects and availability into one line costs it a point.

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 output schema, the description carries the return-shape burden and does so by listing exactly what the preview contains. For a 6-parameter, zero-required read tool, that, plus the scope gate, is close to everything an agent needs; only per-parameter rules (e.g. device_id selection) are left to the schema.

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 only 17%, so the description must compensate, and it largely does by naming the axes the parameters control: linked habitations (habitation_ids), listings/data types (prices, occupation, reservations), period (duration_days) and which browser executes (device_id). The mapping is implicit rather than parameter-named, and the mandatory-when-multiple-browsers rule for device_id stays only in the schema.

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+resource ('Mostra o que uma sincronização coletaria') and immediately negates the tempting confusion with the write sibling via 'Não inicia nada', which cleanly separates it from start_sync. The enumerated content previewed (habitações, anúncios, período, tipos de dado, navegador, cobertura) further pins down the scope.

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 'Não inicia nada' clause implies when to use this instead of start_sync, and the availability line ('INDISPONÍVEL nesta autorização – escopo não concedido ou papel sem o módulo') gives an explicit exclusion condition. It falls short of a 5 because it never names start_sync or states the intended sequence (preview before executing).

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