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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint), the description discloses key behavioral traits: it never places an order, it confirms live price and stock, and it requires a two-step confirmation process. This adds meaningful context that is not captured by annotations alone, helping the agent understand the side effects and state involved.

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 concise and front-loaded with the core purpose ('Two-step exact-SKU purchase prep'). It then explains the two-step flow in two clear sentences and ends with a boundary condition ('It never places an order'). Every sentence earns its place without 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?

The tool has moderate complexity with a two-step flow and no output schema, so the description carries the burden of explaining return behavior. It mentions the outcome ('tracked checkout handoff URL') and implies the first response includes product, live price, and stock. However, it doesn't explicitly describe the exact structure of the first response or possible error conditions, leaving a slight gap. Still, it is sufficiently complete for an agent to use the tool correctly.

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 100% coverage with descriptions for all six parameters, so the baseline is 3. The description adds a bit of context by explaining the role of buyer_confirmed in the two-step flow, but it does not add significant new semantics beyond what the schema already states. It reinforces the purpose of key parameters but does not compensate for any gaps.

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 function: 'Two-step exact-SKU purchase prep.' It specifies the verb ('prepare') and the resource ('purchase handoff'), and distinguishes itself from siblings by emphasizing the exact-SKU and two-step nature. The explicit statement 'It never places an order' further clarifies its scope, separating it from order-placing 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 explicit step-by-step usage instructions: call first with buyer_confirmed=false to confirm product/price/stock, then call again with buyer_confirmed=true to receive the handoff URL. It also clarifies that no order is placed. While it doesn't explicitly name alternative tools, the two-step flow and confirmation requirement give clear context for when this tool is appropriate.

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