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

Annotations only cover the read-only/non-destructive profile, but the description adds substantial behavior: internal 5000-row batching, early stop with nextStartRow for continuation, filter chunking under Google's undocumented filter-size ceiling possibly requiring multiple upstream calls, and collapseVariants recomputing ctr/position across merged rows.

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?

Purpose is front-loaded before the option-by-option detail, and the dense sentences each carry distinct guidance about filtering, paging, or derived fields. It is long and near the upper bound of what is useful, but almost nothing is redundant.

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?

No output schema exists, so the description must carry the return-value burden; it names the metric fields, the nextStartRow continuation mechanism, and the brandedVsNonbranded derived field. It never details a full row shape or how dimensions map to row keys, leaving a small gap for a 10-parameter reporting tool.

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?

With 60% schema coverage, the description supplies meaning beyond the schema for the hardest parameters: `discover`/`googleNews` semantics, searchAppearance as the AI-Overview proxy, the `in` versus regex tradeoff, and the derived brandedVsNonbranded field. A few parameters (siteUrl, rowLimit, endDate) remain unelaborated, but the complex ones are well covered.

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 verb and resource — organic search performance for a property — and enumerates the exact metrics (clicks, impressions, CTR, average position) and dimensions. An agent can distinguish this from GA4-oriented siblings like run_report or get_search_terms 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?

Gives clear operational context: default 28-day window, server-side filtering via pageFilters instead of client-side filtering on a maxed rowLimit, and `in` for allowlists vs regex. It does not explicitly compare against sibling tools (e.g. get_search_terms), so it stops short of full when/when-not routing.

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