search_productsUse when the user names a category by keyword (e.g. 'kraft tape', 'bubble mailer', 'starter kit') with no dimensions. For dimension-based fit, prefer find_packaging_for_item. Returns products with price, stock, URL.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | Free-text search; matches title, vendor, type, tags. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly and openWorld hints. The description adds the return payload (price, stock, URL), which is useful behavioral info absent from the schema. It doesn't mention sorting or edge cases, but the annotation coverage lowers the burden.
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, front-loaded with the core use case, then the alternative, then return info. No filler or redundancy.
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 2-param tool with no output schema, the description covers when to use, what to expect, and an alternative. It lacks limit details and any mention of result ordering or no-match behavior, but is otherwise complete enough for an agent.
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 coverage is 50% (query described, limit not). The description clarifies that query takes a category keyword, aligning with the schema. However, limit's meaning and behavior are not explained anywhere, so the description doesn't fully compensate for the gap.
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 the tool searches products by keyword/category, with concrete examples ('kraft tape', 'bubble mailer'). It explicitly distinguishes from find_packaging_for_item, making the scope unambiguous.
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?
Provides explicit when-to-use guidance: when user names a category by keyword with no dimensions. Also gives a direct alternative: 'For dimension-based fit, prefer find_packaging_for_item.' This is textbook usage guidance.
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 have clearly distinct purposes, but there is potential confusion between inventory-checking tools (check_inventory vs. inventory_status) and cart-handoff tools (create_cart_url vs. prepare_purchase_handoff). Descriptions help differentiate, but an agent might occasionally select the wrong tool.
The naming convention is generally consistent with verb_noun in snake_case (e.g., find_packaging_for_item, get_pricing). However, google_retail_ai_finder breaks the pattern with a company prefix, and some verbs vary (check vs. inventory_status). Overall clear and predictable.
16 tools is slightly above the ideal 3-15 range, but still reasonable for a packaging e-commerce domain covering search, fit, inventory, pricing, shipping, and cart creation. Each tool serves a specific need, so the count feels appropriate.
The tool surface covers the core customer journey: product discovery, fit calculation, inventory/pricing checks, shipping estimation, cart handoff, reordering, and bulk quotes. Minor gaps exist (e.g., no order tracking or cancellation), but these are likely out of scope.