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

Annotations already declare destructiveHint=true and idempotentHint=true, so the agent knows this is an irreversible-but-retry-safe mutation. The description adds genuinely new context: that allocations are released and that the operation is scoped to unissued drafts only. It does not mention permission requirements or whether the cancelled draft is retained for audit, which keeps it below 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?

Three short sentences, zero filler, with the core action and its side effect front-loaded before the use case and the constraint. Nothing needs to be trimmed.

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 4-parameter mutation with no output schema, the definition covers the essential scope but leaves open what the tool returns, what happens to the cancelled draft record afterwards, and what the required reason field is for. Adequate but with real gaps an agent would have to discover by calling.

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 50%: request_id and business_id are documented in the schema, but invoice_id and reason have no description anywhere. The description indirectly constrains invoice_id to an unissued draft, but says nothing about why a free-text reason is required or how it is used, so the gap is only partly compensated.

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 ('Cancel an unissued draft') plus the side effect ('release all its allocations'), which is far more than a restatement of the title. The draft-vs-issued boundary implicitly separates it from invoice_issue and invoice_get, though no sibling is named outright.

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 to rebuild a draft with corrected facts' gives a concrete use case, and 'Issued invoices cannot be changed' is an explicit when-not condition. It stops short of naming the follow-on tool (e.g. invoice_draft) the agent should call to recreate the draft.

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