Submit a quoted order for real McWallet payment under local spending policy; repeated calls reconcile the same checkout to prevent duplicate orders.
REAL PURCHASE: create and McWallet-pay one fresh quoted order within the locally authorized policy. Repeated calls only reconcile.
| Name | Required | Description | Default |
|---|---|---|---|
| account | Yes | ||
| quote_id | Yes | ||
| idempotency_key | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructive=true and idempotentHint=true, and the description meaningfully reinforces the stakes ("REAL PURCHASE") plus a policy constraint not present in structured data. "Repeated calls only reconcile" clarifies the retry semantics beyond the raw idempotent flag, though it doesn't say what a reconcile response actually looks like.
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?
Two tight sentences with the most consequential fact ("REAL PURCHASE") front-loaded. Every clause carries information; the only friction is unexplained jargon like "McWallet".
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?
This is a destructive, real-money mutation with zero parameter documentation and no output schema, yet the description never says how the agent confirms payment success, what a reconcile result contains, or what happens if the quote expired. For a tool that spends money, that leaves material gaps.
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 0%: account, quote_id, and idempotency_key are all bare required strings with no titles beyond the field names. The description only indirectly hints that quote_id comes from a fresh quote and that idempotency_key drives the reconcile behavior; account is never explained.
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 chain and resource: it creates and pays (McWallet) one fresh quoted order, which clearly separates it from checkout_quote and order_pay. It never names those siblings explicitly, so the boundary is inferable rather than stated.
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?
"within the locally authorized policy" and "one fresh quoted order" imply preconditions (an existing quote, prior authorization) but the conditions are not spelled out. Nothing tells the agent when to prefer order_pay over this tool or what to do if the quote is stale.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.