Prepare a Stripe-hosted subscription Checkout URL. It never charges a card. Draft plans, missing owner approval, unavailable covered agents, or missing recurring Price IDs fail closed without creating a session.
| Name | Required | Description | Default |
|---|---|---|---|
| plan_id | Yes | ||
| account_ref | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure. It explicitly states the tool 'never charges a card' and 'fails closed without creating a session' under certain conditions. This is valuable beyond schema and provides critical safety/behavioral information for the agent.
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?
The description is concise, with two sentences that deliver essential information without redundancy. The first sentence states the primary function, and the second provides key behavioral caveats. It is well-structured and front-loaded.
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 simple 2-parameter tool with an output schema, the description is largely complete. It explains the core function, safety guarantees, and failure modes. It does not mention authentication or permissions, but that is often implicit in MCP servers. The only minor gap is the lack of parameter-specific context, already penalized in parameter_semantics.
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 description coverage is 0%, and the description does not elaborate on the two parameters (plan_id and account_ref). It mentions 'Draft plans' and 'recurring Price IDs' but does not connect them to the actual parameter names or explain their formats or required values. The description fails to compensate for the lack of schema documentation.
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?
The description clearly states the tool's function: 'Prepare a Stripe-hosted subscription Checkout URL.' This specifies the verb (prepare), resource (Stripe-hosted subscription Checkout URL), and scope (subscription). It distinguishes itself from sibling tools like customer_portal_link (portal access) and record_subscription (recording), making the purpose unmistakable.
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 provides clear context for when the tool is appropriate (creating a subscription checkout link) and specifies failure conditions ('Draft plans, missing owner approval, unavailable covered agents, or missing recurring Price IDs fail closed'). It does not explicitly name alternatives, but the context implies usage for new subscription checkouts, which is sufficient for a distinct tool.
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.
Most tools have distinct purposes: plan retrieval, checkout, portal, status, usage, MRR. The main overlap is between create_account and record_subscription, as record_subscription can create an account for a new bearer, which may confuse agents about when to call which.
The majority follow a verb_noun pattern (create_account, create_checkout_link, get_plan, list_plans, record_subscription). A few deviate: customer_portal_link (noun phrase), mrr_summary (acronym), and describe_agent (verb but not a subscription action), which slightly reduces consistency.
Ten tools is well within the ideal range for a subscription management server. Each tool covers a distinct aspect of the domain—account, plans, checkout, portals, subscriptions, usage, MRR—so none feel redundant or missing.
The tool surface covers account creation, plan browsing, checkout session creation, subscription activation, status checks, usage summaries, and MRR. A notable gap is the lack of direct update/cancel subscription tools, though this is partially mitigated by the customer portal link, which delegates those actions to Stripe's hosted UI.