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

Goes well beyond the annotations by disclosing that execution is simulated first, that the bank method spawns an accounting task with the IBAN and records the refund in the shop, and that the invoice may be cancelled as a side effect. It stops short of explaining what the simulation returns or how confirmation is performed, which keeps it from a 5.

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?

One dense but front-loaded sentence that leads with the action and then the method mechanics; every clause adds information. Slightly run-on with the parenthetical nesting, but no filler.

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?

The output schema and annotations cover return shape and safety profile, and the description covers the main money paths. For a 15-parameter mutation, though, several user-visible switches (restock, notify_customer, assignee, record_in_shop) are never characterized, leaving an agent to guess their effects.

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 20% across 15 parameters, so the description carries real weight: it explains the card/bank method split and the IBAN requirement of the bank path. But restock, notify_customer, assignee, record_in_shop, shop_account, amount, and the invoice_series/number fields are left entirely to undocumented schema names.

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 ('propose a refund on a web shop order') and enumerates the two settlement paths (card via Shopify Payments, bank via an accounting task). It does not explicitly differentiate itself from nearby write tools such as invoices_cancel or returns_create_awb, but the core action is 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?

'Simulated first' and 'Works on: Support desk' imply a propose-then-confirm flow and a channel restriction, which is useful context. However, there is no explicit statement of when to pick this over invoices_cancel for the invoice side effect, nor when the bank path is preferred beyond the schema's default rule.

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