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

Annotations only say it is a non-read-only, non-idempotent, closed-world write; the description adds the substance the agent needs: the cart is not an order, no payment is taken, the returned link expires after 7 days, and there are 40-line / $5,000 caps. That is meaningfully beyond the structured hints.

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?

One core sentence followed by the crucial non-order disclaimer, then the operational limits — all front-loaded, no filler, and every clause (return value, handoff instruction, caps, expiry) carries information an agent acts on.

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 two-parameter tool with no output schema, the description covers what it creates, what it returns (claimUrl), what it deliberately does not do, and the hard limits including expiry, so nothing an agent needs to invoke it correctly is missing.

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 the baseline is 3; the description pushes above that by adding a constraint the schema cannot express — a $5,000 merchandise ceiling and the 40-line cap on items, which tells the agent when a request must be split or rejected.

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?

States a specific verb and resource ('Create a cart of SKUs and quantities') and names the concrete artifact returned ('claimUrl'), which lets an agent separate it from quote, search_catalog and get_inventory without opening any schema.

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?

Explicitly bounds when-not-to-expect: 'It does not take payment or place an order' and instructs 'Give the shopper the link', making the handoff pattern clear. It stops short of naming the natural alternative (quote) for price-only requests, so routing between the two is left implicit.

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