Phone Expect

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

With no annotations, the description carries the load and does disclose the key behavior: a 2-minute polling lapse triggers a single alarm line to the lead's watcher and pages the person not hearing them. It also explains the implicit fallback expectation window (30 min, VR page open / on stream). It stops short of stating auth requirements or what state persists or how it is cleared beyond the signoff hint.

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 is front-loaded, but the prose is a dense run-on with nested parentheticals and shorthand ('a set, a VR session, a jam', 'phone_watch lead=true') that take effort to unpack. The closing instructions (when to call, signoff) are useful but buried at the end.

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?

An output schema exists, so return values needn't be explained, and the escalation/timeout semantics are well covered. Still, a required parameter (`why`) and the default `minutes` value go undocumented, leaving gaps an agent must guess at before calling.

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 0% across 4 params, so the description must compensate. It gives meaning for `who` and `minutes` (duration of the expectation) and a partial gloss for `by` ('who set it'), but the required `why` parameter is never mentioned at all, and the 180-minute default is not surfaced.

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 core verb+resource is present – declare that a phone watcher for `who` must stay alive for `minutes` – and it is differentiated from phone_watch (lead=true alarm target) and phone_signoff (terminator). However, heavy domain jargon ('watcher must stay up', 'one alarm line goes to the lead's watcher') makes it hard to tell at a glance whether this is a monitoring timer, a presence assertion, or a notification subscription.

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?

'Call it at the start of the set or session' gives explicit timing, and 'phone_signoff(who) ends it' names the sibling that terminates the state. It also notes what happens if you skip it (agents that watched in the last 30 min are expected anyway during VR/stream), which clarifies when it is and isn't necessary.

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