rms_remind

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

With no annotations provided, the description carries the full burden and does substantial work: it discloses that the tool is global rather than per-project, and that responses will asynchronously carry a '[RMS reminder]' block at 30/20/10/5 minutes before and at due time, with an instruction to relay it. What it omits is the destructive semantics of done/cancel (permanent or reversible?), any output shape for the list action, and any limits on stored reminders.

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 purpose and the primary add-a-reminder flow are front-loaded, and the long parenthetical about the timestamp format earns its length by preventing malformed calls. Slightly denser than ideal — the reminder-delivery and multi-action details are packed into one paragraph rather than separated — but there is no filler sentence.

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?

For a five-parameter tool with no annotations and no output schema, the description covers every parameter's role across the five actions and even describes the return channel (the '[RMS reminder]' block) that an agent would otherwise have to discover at runtime. Nothing needed to call any action correctly is missing.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: due_at must be RFC3339 'WITH the user's UTC offset' plus an example value, in_minutes is framed as the relative alternative, and id is bound to exactly the done/cancel/snooze actions. This is more than the schema's terse field blurbs convey.

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 opening sentence names a specific resource ('Personal reminders') and immediately clarifies its delivery model ('that you pass on to the user'), which no sibling tool does. The enumerated actions (add, list, done, cancel, snooze) plus the 'Global, not per project' scoping line make it unmistakable against rms_search, rms_write, or any other sibling.

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 an explicit trigger example ('When the user says e.g. "remind me to call Viktor Petrovich tomorrow at 12"'), which action to call, and an exclusion rule: 'if you do not know the date, time or timezone, ask first' rather than guessing. It also implicitly routes the agent away from this tool for anything not reminder-shaped.

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