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

Annotations only declare the generic safety profile (not read-only, not destructive, not idempotent, closed-world). The description adds genuinely non-structured behavior: the own-week entry is created at once and visible only to that person, while the household version becomes a card other members tap, and `follow` triggers a reminder the evening before or asks who drives. That visibility and side-effect detail is exactly what annotations cannot convey; what's missing is duplicate handling and what happens if the same slot is already taken.

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?

Compact and front-loaded: the routing example comes first, the destination choice and its default second, and the sibling pointer last. Every clause carries information, and nothing is padded. The dense quotation style and the stray `whenText` mention cost a point in clarity rather than length.

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 seven-parameter write tool with no output schema, the definition covers destination choice, privacy, follow-ups, and the alternative tool reasonably well, and the rich per-parameter schema carries the rest. The gaps that matter are the phantom `whenText` reference and the absence of any statement about collisions or repeated adds, given idempotentHint is false.

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 100%, so the baseline is 3, and the description does add real value by documenting the defaulting behavior of `to` that the schema does not. However, it instructs the agent to 'Check `whenText` against what they said', yet no `whenText` parameter exists in the schema (the fields are title, date, time, end). That dangling reference risks an invalid call or wasted reasoning, offsetting the gain from the fallback explanation.

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 concrete action (putting an entry in a calendar) and immediately distinguishes the two destinations it can write to: the person's own week versus the household's calendar that appears as a card in Hem. The Swedish example anchors it in the user's own phrasing, though it takes a beat to decode. It stops short of sharply distinguishing itself from the many other create_* siblings beyond naming create_plan.

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?

Explicit routing is given for the divergent case: 'To gather people instead: create_plan' names an alternative and the condition that selects it. The fallback for omitting `to` (last choice, else own week) is also spelled out so the agent knows what happens without asking. No guidance is given on when to prefer add_to_list or create_event, so the routing is incomplete for the full sibling set.

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