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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: typo tolerance (fuzzy matching) and the shape of the result (up to 10 products with barcode, brand, NCM and link), which an agent needs to interpret results. It stops short of explaining ranking or truncation behavior when more than 10 matches exist.

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?

Two tight sentences with the resource and search mode front-loaded and the return payload second. No filler, no restatement of the tool title, and every clause carries information.

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 listing the returned fields and result cap, so an agent knows what to expect. Annotations cover the read-only profile. The only missing piece is behavior on empty or capped result sets, which is minor.

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%, so the baseline is 3, but the description goes beyond the schema by enumerating what "texto" may contain (nome, marca, tipo de produto) — a real semantic addition for a fuzzy search field. "Devolve até 10" also publicly states the cap that the schema encodes as limite maximum=10.

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 ("Busca produtos no catálogo SI5 Global") plus the matching mode ("texto livre ... tolerando erro de digitação"), which implicitly separates it from the code/NCM lookup siblings. It never names those siblings, so the differentiation is inferred rather than explicit.

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?

"por texto livre (nome, marca, tipo de produto)" implies you should reach for this tool when you have descriptive text rather than an identifier, which contrasts with consultar_codigo_barras and consultar_ncm. However, there is no explicit when-to-use statement, no named alternative, and no guidance on what to do when the search returns nothing.

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