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

Annotations only say readOnlyHint=false and destructiveHint=true; the description goes well beyond them by disclosing that the call is PROPOSED rather than executed, the exact return contract (status='confirmation_required', action_id, plan_token), and that the write occurs only through confirm_action. It also discloses business-state guards (cancelled blocked, paid totals preserved) that materially change how an agent should sequence the call.

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?

Front-loaded with the action and scoped field list, and every clause carries information an agent needs (exclusion, state guards, confirmation contract). The em-dash field list is dense and telegraphic, but given ten undocumented parameters that density is justified rather than padded.

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, multi-parameter mutation with no output schema, the definition covers the write-gating flow, the confirmation return shape, the affected-field scope, and state preconditions. Nothing essential to calling 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?

With schema description coverage at 9%, the description carries the burden and mostly does: it names all ten optional header fields, supplies the due_date format (YYYY-MM-DD), and clarifies seller_legal_entity accepts an id or a name. Gaps remain — it does not explain what payment_terms should contain or how reference differs from your_reference, and it never mentions the required invoice identifier (left to a well-written schema description).

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?

Opens with a specific verb+resource ("Change an invoice's header") and enumerates the exact fields in scope, then explicitly excludes amounts/items/VAT by naming the sibling tool invoice_update_lines. An agent can distinguish this from invoice_create, invoice_cancel, and invoice_update_lines without opening any 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?

Gives explicit routing (lines/VAT go to invoice_update_lines), an inclusion rule ("only what the person asked"), state-based preconditions (cancelled invoices cannot change; paid invoices keep totals), and the mandatory propose→confirm path. When-not-to-update conditions are stated rather than inferred.

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