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

Annotations only declare idempotency, so the description carries the rest and does so well: creating the order does not charge, App channel returns an entry point and original order id with no payment secret string, web channel returns a cashier page, and quote changes force reconfirmation. The no-double-pay and previewHash-confirmation rules add real behavioral context beyond the annotation.

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?

Dense but front-loaded: purchase scope first, then pricing rule, then the preview/confirm flow, then per-channel returns, then verification. Every clause carries information, though the semicolon-chained style and abbreviations make it heavier to parse than necessary.

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 payment-creation tool with no output schema, 7 undocumented params, and only an idempotency annotation, the description covers the crucial gaps: what is not charged, what each channel returns, how to confirm, and how to verify with get_payment_order. Remaining gaps are the meaning of companions and activityRef and any error/expiry handling.

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?

With 0% schema description coverage the description must compensate, and it explains the preview=false/previewHash confirm handshake, what auto does versus app and website channels, and that sourceTicketId must come from this activity and cannot be used for a full-price purchase. It leaves activityRef and companions entirely unexplained, so coverage of the 7 parameters is strong but incomplete.

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 and enumerates the three purchasable kinds (this activity's ticket, the owning organization's annual pass, and post-activity top-up upgrade), which an agent cannot infer from the enum alone. It also distinguishes itself from get_payment_order, which it names as the verification step rather than the creation step.

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 when-to-use context (login required, one of three purchase kinds), a preview-then-confirm workflow, and a failure path ('check the original order, do not pay twice'). It stops short of naming explicit alternatives such as cancel_payment_order or resume_payment_order, so routing between payment siblings is only partially covered.

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