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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered without the description's help. What the description does add is metric semantics, notably that average position is impression-weighted, which is genuine behavioral context an agent would not otherwise know. It stops short of describing the shape of the returned trend (one row per day?) or any row limits.

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 the resource and metric list front-loaded and the time window trailing. Every clause carries information; nothing is redundant with the title.

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, the description usefully enumerates the four headline metrics and the presence of a daily trend, which is enough for an agent to know what comes back. The gap is granularity of the trend series and whether results are site-wide only, but for a two-parameter read tool this is close to complete.

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%, and the `days` parameter already documents its 7-90 range and the 3-day reporting lag in detail. The description only restates that the window is 'the last `days`', adding no format, timezone, or boundary semantics beyond the schema, so the 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?

States a specific resource (site totals: clicks, impressions, CTR, impression-weighted average position) plus the daily trend over a window, which is concrete enough to distinguish a site-level aggregate from query-level tools. However, it never names gsc_search_analytics or insights_compare_periods, so the agent must infer differentiation from the phrase 'site totals' alone.

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?

Usage is only implied: 'site totals' suggests a high-level overview rather than a per-query breakdown, which nudges toward this tool over gsc_search_analytics. There is no explicit when-to-use/when-not statement, no mention of prerequisites like gsc_list_sites for valid siteUrl values, and no guidance on choosing this over insights_compare_periods or bing_search_stats.

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