Set, list or cancel a reminder about a chat

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

Annotations only declare the generic safety profile (not read-only, not idempotent, not destructive, closed-world). The description adds real behavior beyond that: reminders are stored locally and delivered to the user's webhook when due, the no_reply condition is skipped if someone replied, and nothing is sent to WhatsApp. Storage/delivery semantics are exactly the kind of context annotations cannot carry.

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 core identity is front-loaded in the first clause, then it moves through create, condition, and the list/cancel actions with no filler. The telegraphic fragments ('list, cancel.') and stacked parentheticals are dense but every element carries information for an 11-parameter multi-action tool.

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 an output schema present, return values need no explanation, and the description still covers all three actions, storage location, delivery mechanism, the condition enum, and the no-WhatsApp guarantee. Only minor gaps remain, such as whether list scopes by account_id and what cancel does to already-fired reminders.

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 82%, so the baseline is 3, but the description adds meaning the schema does not encode: after_hours and due_at are alternatives for the same due time, and condition=no_reply means the reminder is suppressed if someone wrote after it was set. It also clarifies reminder_id comes from create or list.

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 names the resource (the user's reminders about a chat), the lifecycle operations (create/list/cancel), and the three create inputs, so an agent knows exactly what this tool manipulates. The closing line 'Nothing goes to WhatsApp' implicitly separates it from messaging siblings like scheduled_messages, though it never names that sibling outright.

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?

It gives clear per-action context: create takes chat_id, note and either after_hours or due_at; the no_reply condition fires only if nobody wrote since; list and cancel are named. The 'Nothing goes to WhatsApp' clause signals when not to expect messaging behavior, but no alternative tool is named explicitly, so this stops 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.