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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description usefully adds the privacy/access model — the link is private and opened in a browser by the operator — but omits key behaviors: whether each call mints a new link, whether links expire, and whether repeated calls invalidate prior ones.

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 sentence with no padding, and the key attribute ('private link to a live view') is front-loaded. The trailing relative clause about the browser is slightly winding but does add real information about who consumes the result.

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?

With zero parameters, no output schema, and only a readOnlyHint annotation, the description carries the burden of explaining the return value — a URL, presumably — and it never does. For a tool whose entire output is a link, omitting the return type leaves a meaningful gap even though the concept is communicated.

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?

The tool takes zero parameters, so the baseline is 4. The description does not need to explain inputs, and it correctly implies no configuration is required to obtain the link.

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 conveys the concept — a private live-view link streamed 'through your eyes' — which is distinctive against siblings like look or face. But it names no verb and never states that the tool produces/returns a shareable URL, so an agent must infer that this is an action rather than a passive status. Clear in spirit, imprecise in operation.

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?

No indication of when to call this versus reading the room with look, nor any prerequisite or exclusion. The only implicit guidance is that someone else ('whoever runs you') consumes the output, which hints at a sharing use case but never states it as a condition.

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