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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds real analytic behaviour the annotations cannot: severity buckets (>50%/20–50%/<20%), default sort by absolute clicks lost, and the pattern taxonomy (position_slipped, impressions_collapsed, ctr_dropped, disappeared, mixed). It stops short of stating what happens with an under-populated baseline or how the response is shaped.

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 definition, then progressively finer detail (periods, thresholds, sorting, patterns, use case) — every sentence carries information. The parenthetical asides and the trailing bilingual tag add slight clutter but nothing is genuinely wasted.

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 16-parameter analytic tool with no output schema, the description still conveys the shape of the result (severity classification, pattern diagnosis, ordering) and how baselines resolve, which is what an agent needs to call and interpret it. Minor gaps remain around limit/defaults and error paths for the brand filter, which are left to the schema.

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 above that by explaining the interaction of days/startDate/endDate/compare and the year vs previous baseline semantics in one place, which the schema documents only field-by-field. It adds no guidance on minBaselineClicks or limit, so not a 5.

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?

Opens with a specific verb+resource+scope: "Pages (or queries) that lost clicks between a BASELINE and the RECENT period." It also differentiates itself from neighbouring analysis tools (detect_anomalies, get_ranking_changes, get_page_performance) by stating it ranks by absolute clicks lost and classifies drop severity, so an agent can pick it 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 names the use case ("which pages are dying" and refresh candidates) and explains when to use each comparison mode, including the slow-decay case (compare with 6–12 months ago). It does not name a sibling alternative or state when NOT to use it, which keeps it below a 5.

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