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

The description adds genuinely non-schema information: the required scope (referrals:manage), a risk rating, an explicit side-effect claim ('Efeitos: Nenhum – o código já existe') and a current availability warning. However, that no-effects claim sits uneasily with readOnlyHint=false and 'código permanente' sits uneasily with idempotentHint=false, leaving mild ambiguity about whether calls are pure reads and whether repeat calls differ. These are tensions rather than flat contradictions, so no flag, but they cap the score.

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, front-loaded with the return value and then the use case, followed by compact scope/risk/effect metadata. No wasted prose, though the trailing availability clause reads as templated boilerplate rather than tool-specific guidance.

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 two-optional-parameter tool with no output schema, the description covers what comes back (link plus QR code), the auth scope, side effects and current availability. The remaining gaps are parameter-level (what campaign does to the returned link, whether include_qr defaults to omitting the QR), not conceptual.

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 exactly 50%: 'campaign' is documented as a utm_campaign label, but 'include_qr' has no description at all. The tool description never mentions either parameter, so it contributes nothing beyond the schema and does not compensate for the undocumented include_qr flag — at best it implies a QR is returned by default.

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 description uses a specific verb and resource ('Devolve o link e o QR code de indicação do usuário conectado') and narrows the scope with 'código permanente, sem dados de hóspedes', which separates it from sibling tools such as get_referral_performance and list_referral_programs. It does not explicitly name those siblings, so differentiation relies on the resource noun rather than on routing language.

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?

'Use ao recomendar o Arrumou a proprietários, gestores ou corretores' gives an explicit situational trigger, and the closing note that the tool is INDISPONÍVEL under this authorization tells the agent when not to call it. There is no pointer to an alternative tool, which keeps it short of a 5.

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