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

With no annotations, the description carries the full burden and does so excellently. It discloses the checkout-locking side effect, explains that payment confirmation arrives asynchronously via webhook, and instructs polling get_order for verification. This goes well beyond basic expectations.

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 three sentences that cover purpose, usage, return value, asynchronous behavior, and side effects with no redundancy. It is front-loaded with 'Phase 2 of 2' and 'Finalise', making the core purpose immediately clear.

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?

Given there is no output schema and only two parameters, the description fully accounts for what the tool returns (payment_url), how to use it, its side effect (locking), and the correct follow-up action (poll get_order). It also mentions cancellation handling, making it operationally complete.

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?

The schema provides a description for payment_method (overrides previous values), and the tool description adds semantic value by mapping Yoco to card payments and Ozow to instant EFT. The checkout_id parameter is not elaborated, but the phase context implies it references an existing checkout, and schema coverage is 50%, so this is adequate.

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 role as 'Phase 2 of 2' and 'Finalise a checkout and mint the payment link', with a specific verb (finalise) and resource (checkout). It also differentiates from sibling tools like create_checkout, update_checkout, and cancel_checkout by specifying its unique finalisation step and return of payment_url.

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?

Usage guidance is explicit: it is the second phase of a checkout flow, and it directs the agent to use cancel_checkout if the customer changes their mind, and to poll get_order to confirm payment. This clearly indicates when to use this tool and what alternatives to consider.

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