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

Annotations only say it is not read-only and is flagged destructive, which is thin for a write tool. The description adds real context beyond that: it writes only the caller's own record, is undoable from the same surface, is idempotent ('the same reminder twice returns the existing one'), is delivered on channels chosen in Settings, follows a moved timed event, and returns an ordinary result rather than a plan_token. That is exactly the kind of disclosure 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?

Front-loaded with purpose, then parameters, then undo, then the confirmation policy; each block earns its place. There is mild redundancy in the CONFIRMATION section, which restates the own-record/undo points already made earlier, but the extra length is policy-bearing rather than filler.

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 four-parameter mutation with no output schema, the description covers sourcing, offset semantics, idempotency, delivery, and the confirmation contract. The only real gap is what the caller receives back (e.g., reminder identifier or scheduled time), which matters since there is no output schema.

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 25% (only date has a description), so the description must compensate and does: item_key is sourced from planner_get_agenda, date/days is the listing window, offset_minutes is <= 0 with a default of -15 and date-only items counting from 09:00 local. The behavior of reminders on moving timed events is also explained, which is not inferable from the schema.

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 ('Remind the caller about one item of their Planner agenda') and enumerates the item classes it covers (meeting, personal event, CRM follow-up, task/ERP deadline, imported event). This is far more specific than the title and lets an agent distinguish it from sibling tools like planner_cancel_reminder or planner_book_appointment.

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?

Tells the agent where item_key comes from (planner_get_agenda), that the date/days window must match the listing, and that planner_cancel_reminder is the undo path. It also explains the confirmation model, contrasting immediate execution with tools that 'propose and wait'. It stops short of stating what to do when no agenda item exists (e.g., booking a new event), so it is clear context without full exclusions.

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