churn_risk

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

No annotations are supplied, so the description carries the burden, and it does disclose meaningful behavior: scores are rule-based (atraso, chamados técnicos, tempo de casa, plano) rather than statistical, and the scale is 0–100. That is above the norm for a read tool. It still omits that the tool is read-only, how results are ordered/limited, and what happens when as_of is null.

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?

Three short sentences, front-loaded with the core resource and result, then the methodology note. Every sentence adds something; the only weakness is that the methodology detail sits before the usage hint, which is the less critical part for selection.

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?

An output schema exists, so return values need not be explained, but with no annotations and 0% schema coverage the description should have covered the two parameters and the read-only/pagination profile. For a two-parameter analytical tool it is adequate but leaves real gaps.

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 0% for two parameters, so the description must compensate and it does not: 'as_of' (a snapshot date, defaulting to null/current) is never explained, and 'limit' is only vaguely implied by 'maior risco' without stating it caps the returned list (default 20). The agent must guess both meanings from the field names.

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 specific resource and scope ('Clientes ativos com maior risco de cancelar') plus the payload ('pontuação (0–100) e os fatores'), which is far more specific than the bare name churn_risk. It stops short of differentiating from siblings like churn_reasons, churn_by_segment or retention_cohorts, so an agent must infer the boundary itself.

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 para priorizar ações de retenção' gives a clear use context, but there are no when-not conditions and no mention of the sibling tools it competes with (e.g. churn_reasons for factor breakdowns, retention_cohorts for cohort views). The agent gets a purpose but not routing guidance.

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