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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, and the description goes well beyond that: it names the data source and vintage (ITBI, 2019+), the adjustment method (IPCA-corrected m²), and — critically — the failure behavior when a building has no recorded sales. That fallback disclosure is the kind of operational detail annotations cannot carry.

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 Portuguese sentence front-loads the value proposition and the returned fields, then examples, then fallback — a sensible order. The trailing English block is a condensed restatement that partially duplicates the Portuguese text; it is useful for English queries but is not free of redundancy.

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 no output schema, the description carries the full burden of describing return values, and it does: m² median, sale count, price range, trend, last sale month, unit estimate, neighborhood comparison and building page link. Combined with the no-data fallback and all-optional params, an agent has everything needed to call it and interpret results.

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%, so baseline is 3, but the description adds real meaning: it explains that 'area' drives the unit estimate and that when no area is supplied the estimate falls back to the most-sold unit size, and it clarifies that 'endereco' expects street plus number, with 'slug' as the alternate identifier. That is genuine semantic value beyond the field descriptions.

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 and resource — real sale prices paid for a building/house in São Paulo sourced from ITBI records since 2019 — and enumerates the exact outputs (median m² price, sale count, range, trend, estimate, neighborhood comparison). The phrase 'num prédio' scopes it to a single building, distinguishing it in substance from the street- and neighborhood-level siblings.

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?

Three concrete example queries ('quanto vale meu apartamento na Rua X, 123?', 'por quanto o vizinho vendeu?', 'quanto vale um apê de 80 m² na Alameda Franca, 1633?') make the intended trigger clear. It also discloses the no-data fallback (returns nearby buildings on the same street). It never names vendas_rua, vendas_bairro or comparaveis_endereco as the alternatives for street-wide or comparison queries, so the exclusions are left implicit.

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