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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior context beyond that: the data source is ITBI registry records, the window is a fixed trailing 12 months, and coverage spans 96 districts plus city-level aggregation. It omits error behavior for unknown neighborhood names and any data-lag caveat.

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 purpose and scope are front-loaded in the first clause before the metric enumeration, and every clause carries substantive information rather than filler. It runs long in a single dense block, and the trailing English restatement partly duplicates the Portuguese text, though for a bilingual tool that redundancy has some justification.

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 one parameter, no output schema and closed-world annotations, the tool is simple, and the description compensates for the missing output schema by enumerating the returned indicators instead of leaving returns opaque. Input scope is fully specified. Only edge-case behavior (unknown neighborhood, accent sensitivity) is missing.

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 the single parameter already carries a description with examples, so the schema does the heavy lifting. The prose adds marginal value by expanding the accepted vocabulary (Vila Nova Conceição, Vila Olímpia, Brooklin, Higienópolis) and confirming 'São Paulo' as the city-wide value, but does not cover accent/fuzzy matching or invalid-input handling.

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 a specific resource and metric set: actual ITBI-registered prices paid per m² in a São Paulo district over the last 12 months, plus the derived indicators returned. It is clearly not a generic search tool, but it never names the overlapping siblings (resumo_bairro, ranking_bairros, vendas_rua) or states how it differs from them, leaving that differentiation implicit.

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?

Concrete trigger questions are given ('quanto custa o m² em Moema?', 'Pinheiros valorizou?', 'Tatuapé ou Mooca?') along with the operational note 'uma chamada por bairro', which tells the agent how to handle comparisons. There are no explicit exclusions or named alternatives for cases better served by another tool.

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