create_credit_checkoutCreate a payment link that adds prepaid credits to the authenticated key; a person opens it to pay. Does not charge or fund anything until payment is authorized and confirmed.
| Name | Required | Description | Default |
|---|---|---|---|
| credits | Yes | Whole number of credits to buy, within the published minimum and maximum purchase. Each credit costs the published credit_unit_price_cents; the checkout total is credits times that price. |
Changes observed during successful MCP inspections.
Input schema / properties / credits / descriptionPrevious value: -"Whole number of credits to buy, within the published minimum and maximum purchase. Each credit costs credit_unit_price_cents (see get_access_options); the checkout total is credits times that price."New value: +"Whole number of credits to buy, within the published minimum and maximum purchase. Each credit costs the published credit_unit_price_cents; the checkout total is credits times that price."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the mutation and safety profile are covered. The description adds genuinely useful non-annotation context: the deferred-effect semantics ('Does not charge or fund anything until payment is authorized and confirmed'). It does not cover link expiry, single-use, or reuse behavior, which keeps it from a 5.
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 no filler; the core action is front-loaded and the deferred-charge caveat follows immediately. Every sentence earns its place.
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 exists, but the description implies the return is a payment link a person opens, which is adequate for a single-parameter tool whose fee semantics are already stated. Link lifecycle details (expiry, single-use) would be the remaining gap.
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?
There is only one parameter and schema description coverage is 100% — the schema already explains the unit, min/max, and pricing math. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.
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 ('Create a payment link that adds prepaid credits') and describes the mechanism — a person opens the link to pay. An agent can distinguish this from siblings like subscribe_event or get_credit_balance without opening the schema.
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 description implies its use case (buying prepaid credits via a shareable link) but never states when to prefer it over alternatives such as subscribing via subscribe_event or checking balance first. Usage is inferable but not explicit, and there are no exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.