Compara ofertas vigentes de um produto entre supermercados acompanhados pelo Menor Preço Hoje em Lages, Santa Catarina.
| Name | Required | Description | Default |
|---|---|---|---|
| product | Yes | Produto que será comparado entre mercados. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action ('compares offers') without revealing side effects (likely read-only), output format, pagination, or behavior when no offers are found. The limited information is not misleading but is insufficient for the agent to predict runtime behavior.
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 a single, efficient sentence that front-loads the action ('compares') and the object ('offers of a product'). It includes essential context (geographic scope) without extraneous words. Perfectly concise and well-structured.
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 simple tool with one parameter and no output schema, the description covers the basic function but lacks behavioral details (e.g., whether it returns a list, how it handles missing products) and usage guidance. The absence of annotations and output schema makes the description incomplete for full situational awareness.
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?
The input schema already provides a clear description for the single 'product' parameter ('Produto que será comparado entre mercados'). The tool description adds no additional meaning to the parameter semantics. With 100% schema coverage, the baseline of 3 is appropriate.
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 clearly states it compares current offers of a product among supermarkets, with a specific geographic scope (Lages, Santa Catarina). It uses a specific verb (compare) and identifies the resource (product offers). However, it does not differentiate from sibling tools like search_offers or top_offers, so it loses a point on distinguishability.
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?
The description provides no guidance on when to use this tool versus alternatives like search_offers or best_price. It doesn't mention prerequisites, exclusions, or the appropriate context for choosing this tool. The agent is left to infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
best_price, compare_offers, and search_offers all relate to product pricing and offers, which could cause an agent to choose incorrectly. However, each has a distinct output: best_price for the single lowest price, compare_offers for multi-supermarket comparison, and search_offers for general discovery.
All tools use lowercase snake_case and most follow a verb_noun pattern (compare_offers, list_markets, search_offers). best_price and top_offers deviate slightly by leading with a noun/adjective, but the style remains consistent and predictable.
Five tools is well-scoped for a local price-comparison service, covering discovery, comparison, and market listing without redundancy.
The tool set covers the main user intents: finding the best price, comparing offers, searching products, and listing markets. Minor gaps like retrieving individual market details or historical prices exist but are not core to the stated purpose.