Delete invoice

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 behavioral context beyond those flags: 'this server cannot undo it', payments linked to the invoice lose that link, and stale SyncTokens will cause failures. This fully discloses the side effects of calling the tool.

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 dense but every sentence adds useful operational context: permanent deletion, when to use versus alternatives, SyncToken and idempotency requirements, and linked-payment side effects. It is slightly redundant with the annotations and schema (e.g., 'not idempotent' and the freshness requirement), but it remains efficient and well-structured.

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, non-idempotent mutation tool, the description covers the critical context an agent needs: irreversibility, the correct use case, the prerequisite for a fresh SyncToken, failure mode on repeat calls, and the effect on linked payments. Combined with the output schema and detailed parameter descriptions, nothing essential is missing.

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 input schema already covers both parameters thoroughly, including that invoice_id is the internal Id not DocNumber, and that sync_token must come from a fresh get_invoice call and will fail with error 5010 if stale. The description reinforces the SyncToken requirement but does not add much semantic meaning beyond what the schema provides, so a baseline score of 3 is appropriate.

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 opens with a clear verb and resource: 'Delete an invoice permanently from the company file.' It distinguishes this action from voiding or issuing a credit memo, which are the correct alternatives for invoices the customer has seen, so an agent can immediately understand what this tool does and how it differs from other accounting actions.

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 explicitly states when to use the tool ('only for an invoice raised in error'), when not to use it (customer-visible invoices should be voided or credited), and the prerequisite of a fresh SyncToken from get_invoice. It also warns that a repeat call fails because the invoice no longer exists, which gives the agent clear operational guidance.

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