set_alarm

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

With no annotations, the description carries the full behavioral burden, and it discloses only one trait: the Clock app is not opened, so open_app is unnecessary. It says nothing about whether alarms are additive or overwrite existing ones, permission requirements, or whether a confirmation is returned.

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 with no filler, and the most decision-relevant fact (it sets a real alarm in the Clock app) leads. It is not padded, though it is arguably under-written rather than optimally sized.

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 simple three-parameter device action with full schema coverage and no output schema, the description covers the core action and the headless behavior. It leaves enough unstated about side effects and results that an agent still has to guess at edge cases.

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 description coverage is 100%, and the schema already documents all three fields with time formats and a day-string example. The description adds no parameter meaning beyond that, so the baseline of 3 applies.

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 ("Set an alarm") plus the target surface ("phone's Clock app"), which is enough to distinguish it from neighbors like set_timer or add_calendar_event. It stops short of naming those siblings explicitly, so the differentiation is inferential rather than stated.

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?

There is no guidance on when to pick this over set_timer, add_calendar_event, or schedule_message, which are the obvious confusable siblings. The only contextual signal is the trailing "without opening it" clause, which implies usage but doesn't exclude anything.

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