Subscribe a customer to a plan

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

Annotations already declare the non-read-only, non-destructive, non-open-world profile, and the description adds genuinely new behavior: nothing is debited automatically, invoices are issued at `start_date` then at each period end, and a dedicated virtual account is provisioned for the `dedicated_account` path. The 409 subscription_exists conflict is a useful disclosed failure mode. It does not describe the returned subscription object or confirmation timing.

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 lead sentence 'Subscribe a customer to a plan.' is duplicated immediately, which is pure waste. The `collection_method` explanation largely restates the enum description in the schema. The remaining content is well-structured and front-loads the important scoping facts.

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 an 8-parameter mutation with no output schema and nested `metadata`, the description covers the things an agent cannot infer: the billing schedule, the no-auto-debit payment model, and the duplicate-subscription error. Only the shape of the success response and the `split`/`metadata` semantics are left unaddressed.

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 75% schema coverage the schema already documents most parameters, including the `collection_method` enum values almost verbatim as the description. The description does add real meaning about how `start_date` and `days_until_due` interact across periods, but it says nothing about `split`, `metadata`, or `idempotency_key`.

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 definition states a specific verb and resource ('Subscribe a customer to a plan') and immediately scopes it with billing-cycle mechanics. The distinction from siblings like cancel_subscription or get_subscription is obvious from the verb, though the description never names an alternative explicitly.

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?

It gives clear operational context: the subscription is never auto-debited (push payments), and it explains when to pick `invoice` versus `dedicated_account`. It also surfaces the blocking condition (one live subscription per plan, 409). It stops short of naming sibling alternatives such as create_invoice or create_checkout_session for one-off charges.

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