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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description still adds real value: the required permission scope (reservations:read), explicit risk/effects lines, and a disclosure of what is returned, including that the guest field varies 'conforme papel' (role-dependent). It omits pagination behavior and default ordering.

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 short paragraphs: capability and views first, then return fields, then scope/risk/effects. Nothing is padded and the most important information is front-loaded. Slight redundancy between the view list and the enum names in the schema.

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 return-field sentence is genuinely necessary and present, and permission/effects metadata fills the annotations' gap. But for an eight-parameter tool with 13% schema coverage, the description leaves pagination, filtering by status/habitation, and date/period parameter binding unexplained — an agent could construct a call but not a well-tuned one.

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 only 13% — seven of eight parameters have no schema documentation at all. The description restates the `view` enum in business wording but says nothing about limit/offset (pagination), the `status` filter, or `habitation_ids`, so those parameters remain completely opaque. With low coverage the description needed to compensate and largely does not.

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 first sentence gives a specific verb (list) plus resource (reservations/stays) and enumerates the seven views supported, then lists the fields returned. That is far beyond a tautology. It stops short of a 5 because it never distinguishes the tool from siblings such as list_balance_due (which overlaps with the balance_due view) or get_reservation.

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?

Naming the views ('chegadas', 'hospedados agora', 'saldo devedor', 'canceladas') implies when each mode applies, so usage is inferable. However there is no explicit when-to-use guidance, no mention that arrivals/departures require `date` while `period` requires start/end (that only lives in the schema), and no routing away from list_balance_due or get_reservation despite overlap.

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