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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds materially new behavior: the deletion is irreversible, it requires a claimed Last Price credential with billing write scope, and a sandbox key from self-registration is refused with a 403 until the workspace is claimed. That last detail is exactly the kind of failure mode an agent cannot infer from structured fields.

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 parameter, then the risk, then the auth gates. The opening 'pass invoice_id' is slight duplication of the schema but it does anchor the sentence; there is otherwise no 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, everything an agent needs is present: what it does, that it is unrecoverable, the required credential scope, and the specific 403 precondition. Nothing material 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 description coverage is 100% and the property description already says 'its id, as list_invoices shows it', which the description merely restates as 'pass invoice_id'. No additional syntax, format, or edge-case guidance is offered beyond the schema, so the baseline 3 applies.

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') and immediately names the key parameter. The verb alone cleanly separates it from the cluster of sibling invoice tools (get_invoice, update_invoice, list_invoices, send_invoice), so an agent can route to it without opening the schema.

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 supplies strong preconditions (billing write scope, claimed workspace) and warns that the effect is irreversible, which implicitly signals 'only use when you really mean to destroy'. However, it never names an alternative such as update_invoice or send_invoice, nor states the condition under which deletion is preferable to those — the when-to-use-vs-alternatives guidance is left implicit.

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