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

Goes well beyond the annotations by disclosing the resulting negative-amount invoice, the payment-gateway balance dependency, the default confirmation behavior and how to disable it, the human-in-the-loop requirement, and the required Cotlet API key scope. The only gap is that it doesn't state whether the refund is reversible or how long it takes to settle on the gateway.

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?

Front-loaded with the action and its main consequence, and nearly every sentence carries new information (gateway dependency, negative invoice, send_invoice follow-up, confirmation policy, auth). There is mild redundancy between 'Refund a sale in full' and 'Refunds the whole sale; Systeme.io does not support partial refunds'.

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 single-parameter mutation with no output schema, the description supplies everything needed to call it safely: preconditions (gateway balance), outcome (negative invoice), follow-up (send_invoice), authorization (Cotlet API key with app access), and consent policy.

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 100% and the single parameter (transaction_id) is documented in the schema, including its source ('from list_transactions'). The description adds no further parameter-level detail, so the baseline of 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 ('Refund a sale in full through its payment gateway') and immediately names the side effect (a negative-amount invoice is created). An agent can distinguish this from siblings like send_invoice, get_transaction, and list_transactions without opening any 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?

Gives explicit when/when-not: full refunds only with no partial-refund support, and the gateway balance must cover the amount. It also routes the agent to the follow-up sibling ('which send_invoice can email to the customer') and mandates confirming with the user before each call.

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