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

Goes well beyond the annotations: it discloses one-time use ('the first browser that opens it keeps it for an hour'), a 7-day expiry for unopened links, that the link is a frozen snapshot rather than a live view, a per-recipient-creation policy, and that it is free. These are exactly the facts an agent needs to avoid generating a stale or mis-scoped link, and none of them are in the schema or annotations.

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 tight sentence front-loads the one-time snapshot nature, then expiry, then the per-person rule. The trailing 'Free.' fragment is efficient. Slight density and the missing explicit verb keep it from a 5.

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, non-destructive link generator with no output schema, the description covers lifetime, sharing policy, and snapshot semantics — the parts that matter. It could still state that the response is a URL string and whether the link is publicly accessible without authentication, but the remaining gap is small.

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% — the single `name` parameter is documented with a concrete example ('weekly-sales') — so the schema does the heavy lifting. The description mentions 'saved view' but adds no format or resolution detail (e.g., how name matching works if the exact name doesn't exist), so baseline 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?

The description states a specific artifact — a one-time link to a saved view — captured 'as it is now', which makes the snapshot semantics clear. It does not differentiate from close siblings like view_send_link, view_show, or view_get, and the verb ('creates/returns a link') is only implied rather than stated; the title's 'dashboard' wording also differs from the description's 'saved view'.

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?

'Make one per person' is a genuine usage constraint, but there is no explicit when-to-use / when-not-to-use guidance and no routing against view_send_link, view_show, or view_get, which are the obvious alternatives for sharing or reading a saved view. The agent must infer selection from the description alone.

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