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

Annotations already flag destructive=true and idempotent=false, and the description still adds real substance: the refusal precondition, that billed quantities on the order become billable again, that the books reverse the entry, and the $0.01-per-call price with no charge on failure. That is exactly the kind of side-effect and cost context annotations cannot express.

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?

Two dense sentences, front-loaded with the purpose, then consequences and cost. Every clause carries information an agent would otherwise have to discover by failing a call.

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 two-param mutation with no output schema, the description covers preconditions, side effects, and pricing well. The remaining gaps are the meaning of reason and any hint of what a successful void returns.

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 50%: bill_id is documented as the id purchasing_create_bill returned, but the optional reason field has no description anywhere. The description never mentions reason or what a useful value looks like, so it fails to compensate for the coverage gap.

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?

It names a specific verb (void) and resource (bill) and bounds the applicable case: a bill entered by mistake or replaced. That already separates it from purchasing_update_bill or delete_repeating_bill in spirit, but no sibling is named, so an agent must infer the boundary.

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?

It gives an explicit when (entered by mistake or replaced) and an explicit blocking condition with a redirect: 'refused while money is recorded as paid on it (record the refund first)'. No other tool is named as the alternative for correcting rather than voiding, which keeps it a step below a 5.

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