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

Goes well beyond the annotations by disclosing ordering (longest overdue first), a hard dedupe rule (each invoice at most once per day), the specific reasons an invoice is skipped (no customer email, emailed in past 24h, bounced address), that skipped invoices are reported with why, and the exact cost of $0.02 per reminder sent. These are real operating constraints an agent cannot get from the schema or annotations.

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?

The cost is stated twice in near-identical wording ('$0.02 per reminder sent. Costs $0.02 per reminder sent; nothing if none are found'), which is pure redundancy. The 'one call, or one weekly schedule (schedules_create), chases them all' clause is a run-on that reads awkwardly and slows parsing of an otherwise front-loaded description.

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 usefully signals the return shape (skipped invoices listed with reasons) and the batching semantics of limit and days_overdue. It is close to complete; the only real omission is how this relates to the non-bulk invoices_remind sibling.

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 only 50%, but the description compensates by explaining what days_overdue means (invoices at least that many days past due) and how limit caps the batch. message and link_hours are already documented in the schema, so the remaining gap is minor.

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?

Names a specific verb and resource with clear scope: email a reminder for every sent invoice past its due date with a remaining balance, longest overdue first. The scope is unambiguous, but the description never distinguishes this from the sibling invoices_remind, leaving the agent to infer that one is bulk and the other is single-invoice.

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?

Mentions the schedule option (schedules_create) for weekly chasing, which is genuine usage context, and states that nothing is charged if no invoices are found. However it gives no explicit when-to-use versus invoices_remind or invoices_send, and the phrase 'one call, or one weekly schedule ... chases them all' is ambiguous about whether the schedule is created here or elsewhere.

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