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

Annotations already establish readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description still adds genuine behavioral context beyond that: the results are sorted most-clicked-first, a total page count accompanies the rows, the window is capped at 366 days, and Search Console's omission of rare queries makes totals lower than native Search Console figures. 'It changes nothing' merely restates readOnlyHint and is redundant, and no pagination or page-of-results behavior is described.

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 metric inventory and the 'most clicked first' ordering are front-loaded where the agent needs them, and the caveats about Search Console undercounting and the 366-day cap are compact. The opening sentence is a long accumulation of clauses, and the closing 'It changes nothing' spends a sentence restating what annotations already declare.

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 four flat parameters, no nested objects, and no output schema, the description covers what an agent needs: metric set, sort order, the returned total page count, date-window bounds, and the error condition. The main residual gap is that the agent is not told how to page past the first `limit` results or what the row payload structure looks like, though the metric list largely implies it.

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 75%, with `domain` carrying no description at all in the schema; the description compensates by framing domain as one of 'the organization's connected websites' and by stating the not-found behavior for unverified or unconnected sites. It also adds meaning beyond the schema for `from`/`to` via the 366-day ceiling, and for `limit` by tying it to the 'most clicked first' ordering.

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 names a concrete resource and scope: 'per page over a window of days' for 'one of the organization's connected websites', and enumerates the exact metrics returned (clicks, impressions, CTR, average position, visits, search visits, engagement rate). It does not name a sibling to contrast with (e.g., webops_searches for queries or webops_daily for time series), but the 'per page' framing is specific enough to separate it from those tools.

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?

The description supplies operational constraints — 'At most 366 days', default ordering 'most clicked first', and the failure mode for a site that is 'not this organization's, not verified or not connected to Google' — which effectively tells the agent when the call will not work. It stops short of any explicit routing guidance such as when to prefer webops_searches, webops_daily, or webops_list_websites instead, so usage is implied rather than prescribed.

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