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

With annotations already covering safety, the description adds substantial behavior: the run begins immediately with a Lock Screen card, off-phone steps arrive disabled, allowlisted webhooks must reuse the address/method/secret names exactly, and onNext buttons are also triggered by the person's own Next while next_step won't press them. It never says what calling twice produces, which is the notable gap given idempotentHint=false.

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 purpose and immediacy are front-loaded, then the constraints follow in logical order. Sentences are long and clause-heavy, but each one carries distinct information about steps, webhooks, or button behavior.

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 2-parameter creation tool with no output schema, the description covers the starting behavior, persistence, and step-configuration rules an agent needs to write a valid payload. It stops short of saying what comes back or how to follow the run afterwards (get_run / next_step exist as siblings), leaving a small gap.

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. The description restates the ask_first guidance almost verbatim from the schema and adds only a pointer to how_to_write_a_routine for the 'written' payload, which is marginally useful but not new parameter semantics.

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 states a specific verb and resource ('Starts a run on the person's iPhone from steps you write') and scopes it as a one-off rather than a routine. The distinction from the sibling start_run is implied through 'without making a routine of it' rather than named explicitly, which keeps it just short of a 5.

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?

Concrete use cases are given ('a checklist for today, a test plan, a one-off errand') along with the persistence rule ('stays out of the person's routines unless they keep it') and a pointer to how_to_write_a_routine for the payload format. It doesn't explicitly say when to prefer start_run over this tool, so the alternative is left implicit.

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