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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered; the description still adds real value by disclosing the unauthenticated access model and a concrete 60 req/min rate limit, plus the fact that the underlying data is a weekly audited sample rather than live tick data. It stops short of describing response shape or pagination, which matters given there is no output schema.

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?

Front-loads the verb, scope and fuel list, then moves into clean use/avoid routing. It loses a point for redundancy — the '27 Brazilian states' coverage is restated twice within a few lines ('all 27 Brazilian Federative Units' and again in the station sentence), which is wasted space in an otherwise dense description.

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 read-only query tool with no output schema, the description covers source, geography, fuel taxonomy, computed metrics (70% parity ratio, price dispersion) and rate limits — enough for an agent to decide and call correctly. The one gap is that with no output schema, it never sketches what a result contains (station records vs aggregate stats), forcing inference on how to read the response.

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 100% and each parameter carries its own description including the UF pointer to brazil_list_states, so the baseline is 3. The prose adds modest mapping value by giving the human-readable fuel names (Gasolina Comum, Etanol Hidratado, Diesel S10, GNV) that correspond to the enum values, but nothing on the cidade slug format or statewide-vs-city behavior beyond what the schema already says.

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?

States a specific verb ('Queries') plus resource ('real-time audited retail fuel prices'), names the authoritative source (ANP), and enumerates both the geographic scope (27 UFs, 413 cities) and the exact fuel categories covered. It also names the siblings it is not (brazil_lpg_gas_prices, brazil_freight_logistics), so an agent can separate it from neighbors without opening a schema.

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?

Contains explicit 'When to use' and 'When NOT to use' clauses, and each exclusion routes to a named alternative tool with the differentiator spelled out (LPG cooking gas vs freight rates). The only remaining call — whether a city-level or statewide query is wanted — is handled by the schema default.

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