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

With no annotations, the description carries the full burden and does a good job: it discloses the auth requirement (merchant key), the sandbox/preview behavior of mk_test_ keys, the downstream charging semantics of each collection mode, and what is returned ("the first checkout to hand the buyer"). It omits idempotency/retry behavior and failure modes, which matter for a mutating billing call.

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?

Three dense sentences with the core action front-loaded and no filler; the parenthetical about mk_test_ keys and the mode clause both carry information. Slightly overloaded with parentheticals, but nothing is redundant.

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, 6-required billing tool with no annotations and no output schema, the description covers the operation, auth, mode selection, and return value—enough to call it correctly in the common case. The gaps are idempotency semantics and the productId/planId relationship, which an agent must guess.

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 only 13% (just externalSubject), and the description adds genuine meaning for the collection enum—its two values, which is default, and the mobile-wallet constraint—while implicitly tying provider to PayPal and mobile wallets. But productId, planId, email, phone, and especially idempotencyKey receive no explanation anywhere, so the compensation is partial.

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?

Opens with a specific verb+resource ("Open a subscription for a customer"), which is unambiguous about the operation and the owning entity. It does not explicitly contrast itself with siblings like wavepay_checkout or wavepay_bnpl, though no sibling overlaps its subscription-creation role, so disambiguation is largely implicit.

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 gives real guidance on the collection mode (automatic vs. invoice_and_remind, default, and the mobile-wallet restriction), plus the merchant-key/test-key requirement. However, it never states when to choose this tool over wavepay_checkout, wavepay_bnpl, or wavepay_register, leaving tool selection to inference.

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