draft_payment_reminder

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. The description nonetheless adds meaningful reassurance specific to the email domain — 'nothing is sent' — which preempts the common agent assumption that a reminder-email tool triggers delivery. It still does not say whether the draft is persisted anywhere or returned only as text.

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 short sentences, front-loaded with the action and followed immediately by the most important constraint. No filler, no restatement of the tool name.

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?

An output schema exists, so return-value explanation is not required. However, for a drafting tool with an unexplained tone enum and a 0%-covered schema, the description leaves open what 'final' tone implies and how the produced draft relates to the send workflow — gaps an agent would notice.

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% and the description never mentions either parameter. The 'tone' parameter in particular (friendly/firm/final) carries real semantics — escalation level and likely wording intensity — that the enum values alone do not explain, and the description does nothing to compensate.

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 artifact (write a payment-reminder email) plus the target object (an unpaid invoice), so the agent knows exactly what is produced. The 'Draft only: nothing is sent' clause separates it in spirit from mark_invoice_sent, but no sibling is named and 'unpaid' preconditioning is only implied by the tool name.

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?

Usage is implied by the phrase 'for an unpaid invoice', which tells the agent the precondition, but there is no explicit when-to-use versus when-not guidance. Siblings like overdue_report (identifying which invoices are late) and mark_invoice_sent (actually sending) are not referenced, so the agent must infer the workflow split.

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