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

Annotations already cover readOnly, idempotent, and non-destructive, yet the description still adds substantive behavior: a data-completeness caveat that Search Console omits rare searches so these totals are lower than in Search Console, the 366-day cap, and the exact failure mode for unconnected or unverified domains. The closing 'It changes nothing' merely restates readOnlyHint and earns no credit.

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 description is compact, front-loads the returned metrics, and follows with limits and failure conditions in a logical order. Minor waste remains: 'It changes nothing' is redundant with the annotations, and phrasing like 'answers not found' is slightly awkward.

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 no output schema and only three parameters, the description carries the burden of describing returns, and it does so by enumerating every metric returned per day from each source. Combined with the range cap and the not-found condition, an agent has what it needs to call this correctly and interpret the result.

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?

At 67% schema description coverage, from/to are already documented in the schema with their default window, so the description adds little there beyond the 366-day ceiling. It does add meaning for the undocumented 'domain' parameter by specifying it must be one of the organization's connected websites, which partially closes that gap but does not fully compensate.

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 specific resource and granularity ('for one of the organization's connected websites, per day') and enumerates the six returned metrics from two named sources (Search Console and Analytics). It implicitly distinguishes itself from sibling breakdown tools like webops_searches and webops_pages by being per-day rather than per-query or per-page, but it never explicitly contrasts them.

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?

It supplies real preconditions: the domain must belong to this organization, be verified, and be connected to Google, otherwise the call answers not found. It also states a 366-day maximum range. What is missing is explicit routing guidance — nothing tells an agent when to prefer this over webops_searches, webops_pages, or webops_website_status, so usage must be inferred from the metric list.

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