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

Annotations only declare write/destructive/openWorld flags; the description adds substantial context beyond them — required scopes (write:tickets, plus read:account for the balance preflight), the two-phase preview/confirm contract, what the preview returns (payment_link, checkout_session_id), what confirm returns (stripe_payment_intent), and the explicit need for user approval. It is consistent with destructiveHint=true by gating execution behind explicit approval.

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?

Front-loaded with the trigger and default rail, then progressively discloses the alternative rails, so the most important content comes first. It is dense and heavily parenthetical for a single paragraph, but the length is defensible given four payment rails and a multi-step confirm flow.

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 destructive, nine-parameter purchase tool with four payment modes, the description covers permissions, the preview/confirm state machine, per-rail return values, and client capability constraints. An output schema exists, so return-value detail is a bonus rather than a gap, and nothing needed 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 and the schema already explains each parameter well. The description still adds meaning the schema lacks: rail-selection heuristics, the mpp credential fallback via params._meta when a client cannot send _meta, and the ordering relationship between the preview's checkout_session_id and the confirm call.

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 — buying tickets to an event on the XP marketplace connected order book — and frames it as a purchase flow, which is far more than a restatement of the name. However, it never distinguishes itself from the closely named sibling buy_listing_now, leaving the agent to infer that this tool operates on ticket groups (uvid) rather than listings.

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 states when to use it ('when the user wants tickets to an event'), which rail to pick by default and when to switch ('use stripe_link unless the user asks for another'), and gives a per-rail condition for the non-default options including a caution that x402 should only be used by callers that can sign Solana payloads. The preview-then-confirm sequencing is spelled out as a procedure.

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