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

Beyond the readOnlyHint=true annotation, the description discloses meaningful dynamic behavior: it serves a cached/materialized read when includePending=true and no simulation is requested, otherwise recalculates live in the Python engine. It also explicitly states the simulation modes write nothing ('não grava nada, é só simulação'), which is consistent with — and adds depth to — the annotations. No contradiction with annotations.

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 description is long but every sentence earns its place: core function, cache-vs-live behavior, simulation semantics, and sibling differentiation are each handled in one sentence. It is front-loaded with the primary purpose. Minor blemish: it refers to 'pending=true' where the actual parameter is 'includePending', which could cause a slight mismatch when an agent maps the description to 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?

Given an output schema exists (so return values need not be explained), annotations cover the read-only safety profile, and the schema covers 100% of parameters, the description is very complete. It covers cache/live modes, both simulation types with non-persistence, and sibling differentiation. Only minor gaps remain, such as the parameter-name shorthand and no explicit mention of the 1-12 month constraint (left to the schema).

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 100%, so the schema documents all six parameters in detail (defaults, ranges, JSON shapes, validity conditions). The description adds the framing that simulation parameters impact the projected balance without persisting, and references the months cap, but most parameter semantics are already carried by the schema, so the baseline of 3 applies.

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: month-by-month projection of inflows, outflows, and projected balance ('Projeção mês a mês... de entradas, saídas e saldo projetado'). It also explicitly distinguishes itself from siblings, claiming to be the only tool that returns complete monthly cash/balance and naming spending_projection, networth_projection, current_month_spending, and analytics_history as alternatives.

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?

The final sentence gives explicit routing rules: use spending_projection for expenses-only by category, networth_projection for net worth only, current_month_spending for the current month without future projection, and analytics_history for real historical series. This is direct when-to-use-vs-alternatives guidance tied to concrete sibling names.

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