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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's 'permanently deletes' is reinforcement rather than new info. The real added value is the safety-gate behavior: without confirm:true the call degrades to a preview, and a sent invoice yields 409 — both are behavioral traits not expressible in annotations.

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 tightly packed clauses: WRITE marker, scope constraint, safety gate, then endpoint. Front-loads the destructive nature and every sentence carries distinct information.

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?

Covers mutation semantics, the draft-only restriction, the confirm gate, and the error case, which is enough for a 2-parameter tool with no output schema. It omits permission/auth requirements, but nothing else an agent needs to call it correctly 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?

Schema coverage is 100% and both parameters are documented in the schema, so the baseline of 3 applies. The description's note about confirm:true largely restates the schema's own description of that parameter.

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 deletes a draft invoice') plus the exact endpoint DELETE /invoices/draft/{uuid}. The draft-only scope cleanly separates it from siblings like acube_send_draft_invoice or acube_get_draft_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?

The 'draft only: a sent invoice answers 409' clause tells the agent the precondition and the alternative outcome for non-draft invoices. It stops short of naming the sibling to use for other invoice lifecycles, but the applicability boundary is clear.

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