set_user_prefsSave the shopper's default size and/or fit so they don't re-enter it each time. Args: size (XS…5XL), fit (basic | oversized). Pass only what the user stated.
| Name | Required | Description | Default |
|---|---|---|---|
| fit | No | Fit preference: basic or oversized. | |
| size | No | Default size: XS, S, M, L, XL, 2XL…5XL. |
| Name | Required | Description | Default |
|---|---|---|---|
| fit | No | ||
| size | No | ||
| error | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare write (readOnlyHint=false), non-destructive, and idempotent. The description adds that the preferences persist across sessions ('so they don't re-enter it each time'), which is a behavioral trait beyond annotations. No contradictions.
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 extremely concise: two short sentences. The first sentence states the purpose, and the second describes the arguments. Every word is necessary, no fluff.
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 tool's simplicity (2 optional params, simple types), the description covers the core functionality and usage rule. The output schema exists (though not shown), so return value explanation is unnecessary. Slightly more detail about persistence (e.g., 'saved to user account') would improve completeness, but it's adequate.
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 100%, so parameter names and types are documented. The description adds semantic guidance: pass only what the user stated (implying optionality and avoiding default assumptions) and clarifies the allowed values for size (XS…5XL) and fit (basic | oversized). This provides useful context beyond the schema.
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's action ('Save') on the resource ('shopper's default size and/or fit') with a specific benefit ('so they don't re-enter it each time'). This distinguishes it from sibling tools like 'get_user_prefs' (read) and other cart/order 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 provides clear guidance: 'Pass only what the user stated.' This tells the agent not to infer or fill in missing preferences. It also lists the acceptable args and their formats. However, it does not explicitly state when not to use this tool (e.g., if preferences are already saved), but the context is clear enough for an AI agent.
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.
Tools are mostly distinct; slight overlap exists between cart_update and set_cart_quantity (both modify cart lines), and between remove_promo and cart_remove (different domains). Other groups (studio, designer) are well-separated.
Consistent use of verb_noun pattern for most tools, with noun prefixes (designer_, studio_) grouping related tools. No mixed conventions or obscure abbreviations.
31 tools is high for a single server, covering shopping, studio, and designer domains. Some tools like cart_update and set_cart_quantity seem redundant, pushing count beyond optimal.
Core workflows (search, cart, checkout, generation, designer submission) are covered. Minor gaps: no edit/delete for designs or orders, and no tool to manage saved addresses beyond viewing.