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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered. The description adds genuinely new behavioral context: the tool itself charges nothing and sends no prompt, and the actual payment happens when the human opens the returned link and sees the exact charge. That clarifies the human-in-the-loop nature of the operation, which annotations could not convey.

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, front-loaded with the purpose and eligibility, then the human-payment mechanism, then the parameter-lookup guidance. Efficient and well ordered, though the payment-mechanism sentence is slightly verbose relative to the rest.

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?

With no output schema, the description correctly carries the return-value burden by stating it returns the payment page link. Eligibility, the no-charge/no-prompt caveat, and how to supply each lookup key are all present. Only minor gaps remain, such as whether the link expires or how long it is valid.

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% and all three parameters are documented in-schema, so baseline is 3. The description goes further by explaining the lookup logic: orderId comes from list_my_orders, and restaurantId is only needed alongside orderCode when the same code exists at two venues. That disambiguation rule is real added meaning 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?

States a specific verb and resource (returns the payment link for a WaitApp payment page) and sharpens it with eligibility criteria: only the connected person's own orders that still have an amount to pay now, either an online-payment order or a pre-order with a deposit. This scope is distinct enough from sibling get_ticket_checkout_link that an agent can route between them without opening schemas.

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?

Gives clear context for when the tool applies (orders with an outstanding amount) and explicitly disclaims behavior that might otherwise attract the agent away from it: it charges nothing and sends no payment prompt. It also directs the agent to list_my_orders as the orderId source. What it lacks is an explicit exclusion or alternative for the ticket-payment sibling, leaving one routing decision to inference.

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