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

Annotations only declare readOnlyHint=false and destructiveHint=true, which is thin for a state-mutating tool. The description adds the crucial behavior: no e-mail is sent, the operation is only proposed, it returns status='confirmation_required' with an action_id and plan_token, and nothing is written until confirm_action is called.

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?

Four short sentences, front-loaded with the state change and the non-e-mail clarification, then the confirmation mechanics. No filler and no repetition of the schema or annotations.

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 one-parameter mutation gated behind a propose/confirm flow, everything an agent needs is present: the resulting state, what it does not do, the token-based confirmation response, and which sibling completes the write. The lack of an output schema is compensated by the described return fields.

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?

The single parameter is fully documented in the schema (number as spoken, e.g. INV-12 or 12, or its id), and the description adds nothing further to parameter meaning. With 100% schema coverage, this is the expected baseline rather than a 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?

States a specific verb and resource ('Mark an Open/Draft invoice as issued... status Sent') and immediately negates the most likely misreading ('It does NOT e-mail anything'), which distinguishes it from mail_send. An agent can tell exactly what changes and what does not.

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?

Explicitly routes the agent: if the goal is to actually deliver the invoice, use invoice_get for the PDF instead; if the write is intended, the propose→confirm path via confirm_action is named. Both the action and its alternative are stated with selection conditions.

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