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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds materially: what each result carries (price nullable = 'sob consulta', versão, cor, plateEnd, financing, tradeIn, images, storeId), and the critical business constraint that the platform does not sell or finance. That is real behavioral context beyond the structured hints.

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-loaded with purpose, then result shape, then the visit workflow — a sensible ordering. It is dense but nearly every clause carries information; the only mild redundancy is repeating enum values already present in 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?

For a 15-parameter, no-output-schema search tool, the description supplies the return shape, the null-price convention, the store-negociation boundary, and the follow-up call sequence. An agent has everything needed to call it and act on results without guessing.

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 description largely restates the schema-documented filters (make, model, year range, price, mileage, transmission, fuel, bodyType, city) with the same example values. The one genuine addition is the partial-name matching hint for model ('onix', 'hb20'), which the schema also states. Baseline 3 is right; limit, region, and district are not mentioned but are fully documented in the schema.

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 + resource ('Busca veículos à venda') and immediately enumerates the searchable facets (marca, modelo, ano, preço, km, câmbio, combustível, carroceria, cidade), so an agent knows exactly what surface this covers. It is clearly a vehicle-catalog search, distinct from catalog siblings like search_properties, and it names the downstream tools (check_availability, create_cart) for the visit flow.

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?

Gives explicit next-step routing: to see the car or book a test drive, consult check_availability (productId + storeId) then build create_cart with fulfillment 'visit' and scheduledFor. It also sets the boundary that price/financing/trade-in are negotiated with the store, so the agent won't promise those. It does not state when to prefer search_products or get_store_portfolio instead, so no explicit exclusion.

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