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

Beyond the readOnlyHint=true annotation, the description discloses significant behavioral detail: the return can be null, at most one item is ever returned, selection follows a fixed priority order with exact numeric thresholds (100% budget limit, R$50 and 15% variation), and the tool is intentionally scoped to a single highlight rather than exhaustive analysis. This goes well past what annotations convey and fully sets agent expectations.

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 sentences, both dense and purposeful. The first front-loads the core behavior and enumerates the priority rules with clear numbering and thresholds; the second adds the intended use case and sibling routing. The sibling list is long but earns its place as the exclusion guidance, and no redundant or filler content appears.

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?

The tool is simple on inputs (0 params) and has an output schema to cover the return shape, so the description's job is to explain selection logic, null behavior, and scope — all of which are fully specified. The only conceivable gap, exact output formatting, is covered by the existing output schema. An agent has everything needed to decide when to call it and what to expect.

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 has zero parameters and an empty input schema, so per the baseline rule for 0-param tools this scores 4. There is nothing for the description to add about parameters; instead it productively uses that space to explain output behavior. No parameter documentation gap exists.

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 states a specific verb and resource — 'Devolve NO MÁXIMO um destaque textual' (returns at most one textual highlight) — and precisely defines the selection behavior via an enumerated priority list: overdue unpaid bills, then most over-budget monthly budget (>100%), then top spending-growth category (≥R$50, >15% variation). It also distinguishes itself from the sibling family by naming behavior_insights and the anomaly-specific tools it is not.

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?

Usage context is explicit: 'Pensado pra UI de destaque do dia, não para análise completa' — it is designed for a daily-highlight UI, not full analysis. It then gives both the positive route (use this for a single daily highlight) and the negative routes with named alternatives: behavior_insights for all behavioral alerts, and bill_anomalies/subscriptions_overview/transport_routine/bill_concentration/best_card_day for specific anomaly categories. Nothing is left to inference.

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