store_infoStore policies and basics: where checkout happens, and links to the shipping, returns/refund, terms, and privacy pages. Use for "do you ship to X", "what is your return policy", or "how do I pay".
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| store | Yes | ||
| checkout | Yes | ||
| policies | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful context about what information is returned (checkout location and links to policy pages), which goes beyond the structured annotations. It does not describe response formatting, but the output schema handles that.
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 sentences, with the core content front-loaded and the usage guidance immediately following. Every clause earns its place with specific examples rather than filler.
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 parameterless, read-only informational tool with an output schema and full annotation coverage, the description includes everything needed for correct selection and invocation. The examples cover shipping, returns, and payment—the central store-policy use cases.
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 tool has zero parameters, so the baseline is 4; there is nothing for the description to add. The examples clarify the kind of queries it answers, which indirectly confirms no parameters are needed.
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 states a specific resource ('Store policies and basics') and enumerates actual contents (checkout location, links to shipping/returns/terms/privacy pages). It also gives concrete example intents, making its purpose unambiguous and clearly distinct from product- and cart-oriented sibling tools.
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 explicitly says 'Use for' followed by three representative questions ('do you ship to X', 'what is your return policy', 'how do I pay'). This directly tells an agent when to select this tool, and because all siblings are product/search/cart related, no exclusion is needed.
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.
Most tools target distinct actions: browse, search, product detail, inventory, recommendations, cart, and store policy. The main potential confusion is between get_product and check_inventory, which both report product/variant price and stock, though list_products vs search_products is reasonably clear from descriptions.
Tool names are consistently snake_case and many follow a verb_noun pattern like check_inventory, get_product, list_products, and search_products. However, best_sellers, related_products, and store_info are noun phrases, while fetch and search are bare verbs, making the naming pattern mixed but still readable.
Eleven tools is well-scoped for an e-commerce shopping assistant covering catalog browsing, product search, inventory checks, recommendations, cart assembly, content search, and store policies. Each tool has a clear purpose and the count is neither bloated nor too thin.
The tool set covers the full shopper-facing journey: discovering categories and products, searching content, viewing product details and stock, seeing best sellers and related items, checking store policies, and building a cart. As a read-only storefront gateway, missing merchant-side operations are outside its stated purpose.