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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, making the description's 'leitura' redundant. But the description adds genuine behavioral context beyond annotations: exact per-action parameter requirements (e.g., 'checkout_options (product_id + section)'), the section enum values, the '[Flattened action: get]' scoping note, and bulk execution support via plural ID arrays. No contradiction with annotations.

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 description is compact and logically front-loaded: purpose, then the action/parameter matrix, then the current-action note, then bulk behavior. Every sentence carries information and the structure is easy to scan despite the dense semicolon-separated notation. The Portuguese language adds a minor parsing burden but does not obscure the structure.

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?

Given the complexity — 12 parameters, 8 actions, 0% schema coverage, and no output schema — the description covers the action/parameter matrix and bulk behavior reasonably well. But it leaves notable gaps: the 'account' parameter is entirely undocumented, return values are not described despite the absence of an output schema, and the relationship to the 8 overlapping sibling tools is unaddressed.

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?

With 0% schema description coverage, the description carries the full burden and compensates well: it maps each action to its required parameters (list uses name/type/marketplace_id/is_hidden/cursor; get uses product_id; etc.), explains the section enum, and documents bulk support for product_ids/offer_ids/marketplace_ids. However, the 'account' parameter appears in the schema but is never mentioned in the action list, and 'type'/'is_hidden' lack value ranges.

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 opens with 'Produtos e ofertas no Guru (leitura)' — a clear read-only scope over products and offers, then enumerates 8 specific actions (list, get, subscription_options, etc.) with their required parameters. This distinguishes it from siblings at a resource level. However, the multi-action listing somewhat conflicts with the tool name 'guru_products_get' and the '[Flattened action: get]' note, creating mild ambiguity about whether this is one tool or eight.

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?

No guidance is given on when to use this flattened tool versus the nearly identical sibling tools (guru_products_list, guru_products_offer, guru_products_subscription_options, guru_products_checkout_options, etc.). The action→parameter mappings imply how to invoke each action but offer no when/when-not tool-selection advice — a critical gap given the 8 overlapping sibling names.

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