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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses that the MCP is a stateless proxy, Shopify owns the cart state, and the cart_access_token is required for subsequent operations. This adds significant behavioral context not available in the structured 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?

Three sentences, each earning its place: purpose, stateless proxy context, and token retention guidance. Front-loaded and free of 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?

Given the nested schema and no output schema, the description addresses the key operational need—returning and retaining the cart_access_token—and explains the stateless behavior. However, it does not describe the full response shape or error conditions, so it is not fully complete.

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 description calls line items 'selected variant line items,' which hints that item.id is a variant ID, but does not explain the cart object structure or quantity semantics. Schema coverage is only 50% (meta has a description, cart does not), so the description partially compensates but leaves room for clarification.

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 uses a specific verb and resource: 'Create a Shopify-owned cart for selected variant line items through the configured Shopify Cart/Storefront MCP endpoint.' It clearly distinguishes this from sibling tools like get_cart and update_cart by focusing on creation and referencing the token needed by those 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 explains the sequence: create the cart, retain the returned cart_access_token, and notes that get_cart and update_cart will refuse to work without it. This provides clear when-to-use guidance and references alternatives, mirroring the high-quality example in the calibration.

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