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

Goes well beyond the annotations by disclosing irreversibility, the concrete side effect that the client's link stops working, and the server-side guard that rejects invoices with payments. These are exactly the consequences an agent must know before invoking a destructiveHint 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?

Three short sentences, front-loaded with the action and precondition before the consequences. Minor repetition between 'for good' and 'it cannot be undone' is the only waste.

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 single-parameter destructive tool with no output schema, the description covers validity, irreversibility, and side effects. It is silent on what a successful response returns or how refusal is surfaced, but nothing essential to correct invocation 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?

Only one parameter and schema description coverage is 100%, including the 'From list_invoices' provenance note, so the schema already carries the semantics. The description adds nothing about invoice_id format or source, which is acceptable given full coverage but earns only baseline.

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 (delete an invoice) plus a precondition (has no payments) that separates it from a general removal. The resource name distinguishes it from the sibling delete_estimate without ambiguity.

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?

Clearly implies when this is valid (invoices without payments) and when it will be refused (invoices with payments recorded). It does not name an alternative path for the refused case, such as voiding or updating, so the agent is left to infer the fallback.

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