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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description still adds genuine value beyond that: it warns that only rules that are actually configured are returned, that values are not guaranteed, and that the tool may be unavailable without the opportunities:read scope. Missing are return shape and pagination, so this is useful supplemental context rather than rich behavioral disclosure.

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 content summary is front-loaded in the first sentence, followed by the data-quality caveat and a compact scope/risk/availability line. It is slightly boilerplate in tone and mixes two languages, but no sentence is redundant for an agent deciding whether and how to call it.

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 and no parameters, the description carries the burden of describing what comes back, and it does name the fields each program record exposes (rule, formula, currency, release conditions) plus a filter caveat (only configured rules). The availability/permission warning is unusually helpful for a read tool. It stops short of describing list size, ordering, or response envelope, which keeps it below a 5.

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?

The tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly adds no parameter noise.

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 names the resource indirectly ('Programas comerciais ativos no ecossistema Arrumou') and lists what each record carries (regra, fórmula, moeda, condições de liberação), but never states the verb 'list' or the exact entity from the tool name ('programas de indicação'). An agent can infer it returns configured referral/commission program definitions, but the purpose is phrased as a content summary rather than a clear action statement, and no sibling is differentiated.

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?

There is no explicit when-to-use guidance and no routing to alternatives such as get_referral_performance, get_commissions, or create_referral_link. The only conditional information is the authorization caveat ('INDISPONÍVEL nesta autorização'), which tells the agent when the call will fail but not when to choose this tool over another.

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