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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description adds real value by disclosing that results always come from the live Google API (relevant given the sibling search_analytics_archive) and by explaining anonymized-query accounting that makes totals diverge from row sums. It does not cover auth scope or rate limits, keeping it short of a 5.

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 core answer (one total, four metrics) and then the reconciliation caveats in order of likely confusion. The multi-sentence explanation of page-level double counting is a bit long, but it prevents a concrete misreading rather than padding.

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?

An output schema exists, so return shape needn't be restated; the description instead spends its budget on the things an agent would otherwise get wrong — filter semantics, anonymized traffic, and why totals won't equal summed rows. Nothing needed to call it correctly is missing.

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%, so the baseline is 3; the description earns a point by explaining dimension_filter_groups semantics beyond the schema — an inline worked page-filter example and the rule that a query filter never matches anonymized queries. Date, site_url and search_type are left to the schema, which is reasonable given coverage.

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?

States a specific resource (property-wide totals) and enumerates the exact metrics returned (clicks, impressions, CTR, average position), then explicitly says there is no breakdown by query or page. That contrast with search_analytics_query lets an agent distinguish it from the sibling without opening the schema.

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?

Explicitly frames when to use it (property-wide total) versus the alternative (rows from search_analytics_query), and explains the conditions under which the numbers will and will not reconcile with that tool. The filtered case is covered with a concrete example, leaving little to inference.

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