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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral value beyond that: a hard result cap ('até 20 softwares por chamada'), a deterministic ordering ('ordem alfabética'), and the shape of each returned item. It omits total-match counts and any rate limits, keeping it short of a 5.

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 usage trigger, then filters, then return shape, then the sibling redirect — a clean information hierarchy. It is somewhat dense in a single flowing block, but every sentence carries distinct payload and nothing is repeated.

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?

There is no output schema, and the description compensates by enumerating the returned fields (resumo factual, fornecedor, categorias, menor preço publicado, url_canonica) plus the pagination cap and ordering. Combined with the schema-documented filters and the safety annotations, an agent has everything needed to call it correctly.

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%, and the schema already documents every filter including the enum values and the accent/case-insensitive matching rule. The description only restates the filter categories (categoria, tipo, plataforma, preço máximo) and the 20-per-page size, adding no syntax or format detail. Baseline 3 applies when the schema carries the semantics.

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 softwares no catálogo publicado da Softoteca') and scopes it (catálogo brasileiro B2B/B2C, preços em reais). It also names the sibling boundary explicitly, pointing to obter_ficha for per-item detail, so an agent can separate it from alternatives without reading either 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?

Gives an explicit trigger ('Use quando a pessoa pedir indicação, lista ou opções de software para uma necessidade') with concrete examples ('controle de ponto', 'ERP', 'emissão de nota fiscal'), and routes the detail-seeking case to obter_ficha. When-to-use and when-to-use-something-else are both covered.

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