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

With no annotations, the description carries the full behavioral burden; it does declare 'Read-only' and explains what the user will see (annotated screen, per-step captions). It does not say whether the link expires, whether the phone must be started, or whether the user needs their own authorization to open it — meaningful gaps for a link-generation tool.

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?

Front-loaded with the essential concept (a live-view link) before the detail and the usage hint. Three short segments with no filler, though the 'for the user:' interjection slightly interrupts the flow.

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, read-only tool with no output schema, the description covers purpose, read-only nature, and when to offer it — enough to call correctly. The only real omission is link lifetime/expiry behavior, which an agent might want before promising a persistent view.

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 single phone_id parameter is documented in the schema as 'ph_…'. The description adds nothing about the parameter, so the baseline of 3 applies — the schema does all the work.

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 concrete output — 'a link to watch the phone live' — and elaborates that the view shows the phone's screen with your actions overlaid (cursor, taps, swipes, typed text) plus a caption per step. This clearly separates it from screenshot (static capture) and observe, even though those siblings are never named explicitly.

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?

'Offer it when the user wants to see or confirm what you do' gives a clear triggering condition tied to user intent rather than agent preference. It stops short of stating when not to use it or naming screenshot/observe as the alternative when a static image would suffice.

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