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

The description discloses the real-world side effect ('This sends a real email to a real person') and the status change, adding context beyond annotations. Annotations already indicate readOnlyHint=false, but the warning about real email is valuable and consistent.

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 sentences, no waste, and the critical usage condition is front-loaded. It efficiently conveys the action, the condition, and a caution. Excellent structure.

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?

The tool is simple with no output schema, and the description covers what happens (sends email, changes status) and the required precondition. Nothing an agent needs to call 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?

The input schema already has 100% coverage with descriptions for all three parameters. The description adds minor clarification about to_email being a fallback when no billing email exists, but does not add substantive meaning for message or invoice_id beyond what the schema provides. Baseline 3 is appropriate.

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?

The description clearly states the tool sends an invoice with a Stripe payment link to the client's billing email (or to_email) and changes the status to sent. It explicitly distinguishes this from draft-related tools by requiring prior review, so an agent can tell it apart from invoice.create_draft and invoice.preview_draft.

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 provides explicit when-to-use guidance: 'Use this only after the user has reviewed the draft and asks to send it.' It also warns against re-sending unless asked. This is strong, direct usage direction.

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