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

Annotations already flag this as non-read-only, destructive, and open-world, but the description adds a crucial practical warning: 'This sends a real email.' That goes beyond the structured safety hints and is exactly the kind of side effect an agent needs to see. It stops short of describing permissions or irreversibility of the sent email.

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 compact sentences with the side-effect warning front-loaded, the tone options listed efficiently, and the return value summarized in one clause. No filler or repetition.

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?

With no output schema, the description correctly explains what is returned (total reminders sent on the invoice). For a two-parameter tool, it covers the essential context well. The only shortfall is that it does not expand on tone semantics or possible error conditions, which would be useful given 0% schema description coverage.

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 0%, so the description must carry more weight. It clarifies the invoice_id context (unpaid invoice) and enumerates tone values, but the schema already defines the tone enum and default. It does not explain what each tone means behaviorally (e.g., escalation or final notice consequences), leaving a gap that a low-coverage schema does not fill.

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 (send a payment reminder email) and scopes it precisely to the customer of an unpaid invoice. It is clearly distinguishable from siblings like send_invoice or mark_invoice_sent without opening their schemas.

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 implies a clear precondition (the invoice must be unpaid) and exposes the tone choices, giving the agent enough context to decide when this tool applies. It does not name alternatives or explicitly state exclusions, such as not using it for paid or cancelled invoices, so it falls short of a 5.

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