loan_payback

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

Annotations already mark this as destructive and non-idempotent, but the description adds important context: the loan amount is reduced, the guarantee may be released, and the function returns updated loan details. It also explains the preview-then-confirm behavior, which is critical for safe execution. This goes beyond the structured annotations and fully discloses the mutation's side effects.

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 compact and well-structured: it opens with the core action and effects, then immediately provides the prerequisite call, then the private confirmation flow. Every sentence adds useful information, and there is no redundant or filler content.

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 destructive mutation with no output schema, the description covers the essentials: what the operation does, its side effects, how to get the required order_id, and the confirm protocol. The idempotency_key and jwt are documented in the schema, so nothing critical is missing. An agent has enough information to invoke this tool correctly and safely.

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%, so parameter descriptions already exist. The description adds value by explaining that order_id comes from loan_get_orders and by describing the confirm workflow (first call without confirm=true is a preview, then confirm after user agreement). This supplements the schema without repeating it.

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 action ('Pay back (return) part or all of a loan') and the resource (a loan), and specifies what happens: the loan amount is reduced and the guarantee may be released. It also distinguishes itself from siblings like loan_create and loan_increase_guarantee by describing repayment behavior, and points to loan_get_orders for setup. This is a specific, unambiguous purpose.

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 concrete guidance: use loan_get_orders to retrieve order_id or check current loan details before paying back. It also outlines the confirm/preview workflow. It does not explicitly name alternative tools like loan_create or loan_increase_guarantee, but the context is clear enough for the agent to know when repayment is the appropriate operation.

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