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

Annotations only declare the non-read-only, non-destructive, non-idempotent profile; the description adds genuinely new behavior — the proposal is surfaced to the person for approval, or auto-saved if the assistant is configured that way, plus a ~30,000 character size cap. What it does not cover is whether a saved proposal returns an identifier or how the agent learns of the outcome.

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?

A single front-loaded sentence carries the action, format reference, user-review behavior, auto-save exception, and size limit with no filler. Every clause earns its place.

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 one-parameter mutation with no output schema, the description covers format, approval flow, and size limit — enough to invoke correctly. The only omission is what the call returns or how the agent detects save vs. pending review.

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?

With one parameter at 100% schema coverage the baseline is already 4, and the description adds real constraints beyond the schema: no `from` field and a length ceiling. It does not further explain the `written` JSON shape because the schema already does.

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 opens with a specific verb+resource ('Suggests a new routine for the person's iPhone') and pins the format to the sibling reference tool how_to_write_a_routine. It implicitly separates itself from propose_routine_change via 'new' but never names that sibling explicitly, so the distinction is left to inference.

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?

The description conveys the workflow (phone shows it, person saves or drops) but gives no explicit when-to-use versus when-not guidance, and does not contrast itself with propose_routine_change or find_starter_routine. Usage is implied rather than stated.

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