payments_delete

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

Goes well beyond the annotations by naming the cascade effects: the invoice's amountPaid and balance are recalculated and status may revert to 'unpaid' or 'partially_paid'. It also restates irreversibility in plain language, so the agent understands a correction mutates the parent invoice, not just the payment row.

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 short sentences, front-loaded with the action, followed by side effects and then the risk warning. No filler and nothing repeated.

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, idempotent mutation with no output schema, the description covers the essential consequence set: permanent removal plus invoice recalculation and status rollback. Minor residual gaps are what the call returns and any permission/ownership requirements, but nothing that would cause an incorrect invocation.

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 description coverage is 100% and all three properties carry their own descriptions (including the helpful cross-reference that paymentId comes from payments_list). The description adds no further parameter meaning, so the baseline 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 ('Permanently delete a recorded payment from an invoice'), which cleanly separates it from payments_create, payments_list, and payments_receipt_issue. The scope qualifier 'recorded ... from an invoice' makes clear it operates on an existing payment tied to an invoice.

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?

'use with caution for corrections' hints at the intended scenario (fixing mistaken payments rather than routine flow), which is useful implied guidance. However, it names no alternative — e.g. whether to reverse via storno or a receipt refund path instead — and gives no preconditions or exclusions.

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