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

Goes well beyond the annotations by disclosing both return shapes (Stripe URL vs invoice fields), the fact that repeat calls reuse the open checkout or invoice, that the invoice is also emailed, and that payment is not delivery because a human reviews the order after funds clear. This is exactly the mutation context an agent needs before calling.

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?

Four sentences, no filler, front-loaded with the action and then branching cleanly into the card path, the wire path, and the idempotency/review caveats. Every sentence carries distinct information.

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?

No output schema, but the description fully describes what comes back in both branches, plus the idempotency and fulfillment caveats. Nothing an agent needs to invoke it or explain the result to a buyer 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?

One parameter at 100% schema coverage, so the schema already documents order_token and its origin. The description adds only the 'accepted order' state constraint, which is a marginal increment over the structured data.

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: 'Start payment for an accepted dataset order.' It also distinguishes the two payment paths (card checkout_url vs bank-wire invoice), which no sibling tool covers.

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 precondition ('accepted dataset order') plus the schema note tying order_token to quote_training_dataset makes the entry point clear, and 'never collect card details in chat' is an explicit exclusion. It never names a sibling alternative (e.g., create_4k_checkout for 4K licensing), so routing between the two checkout tools is left to inference.

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