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

Adds cost ($0.02 per call, free on failure) and a per-invoice daily rate limit, neither of which is expressible in the annotations. It also makes clear the tool sends a real external email carrying amount due, due date and pay links, supplementing openWorldHint=true with concrete consequence.

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, front-loaded with the action and its precondition, then the limit and cost. No filler and nothing repeated from the title.

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?

Covers preconditions, external side effect, rate limit and pricing for a mutation tool with no output schema. It leaves the failure response and whether reminders are logged/visible unspecified, which is a minor gap.

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 coverage is 100%, so invoice_id, to, message and link_hours are already fully documented. The description only implies what the email body contains, adding no parameter-level meaning beyond the schema baseline.

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: email a payment reminder for a sent invoice with an outstanding balance. It does not name invoices_remind_overdue, so the boundary against that sibling must be inferred from the word 'balance' versus 'overdue'.

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 a concrete precondition (invoice must be sent and still have a balance) and an operational limit (at most once a day per invoice). It stops short of naming the alternative for overdue cases or stating when not to remind at all.

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