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

Goes well beyond the annotations: explains the shared 24-hour cache, that a miss/expired entry or fresh:true fetches billed external provider data and writes the cache, that fresh:false does not guarantee cache-only access, that retries repeat provider work, and that no Scan allowance is consumed. This context is essential given readOnlyHint=false (side effects from billing/cache writes) and adds value the annotations cannot convey.

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-loads the core content (what is returned) before caveats, and every sentence carries substantive information about scope, caching, and billing. It is dense and somewhat long, but there is little redundancy or filler.

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 tool with caching, billing, and provider side effects, the description covers return contents, cache/billing behavior, region defaults, and scope limits. Even though an output schema exists, the description's explanation of what is and isn't returned (AI Overview text omitted, totalResults is an estimate) makes it fully complete for correct invocation.

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?

Although schema coverage is 100%, the description adds meaning beyond the schema: 'fresh:false does not guarantee cache-only access' reframes the fresh param, and 'omitted/GLOBAL region targets the US, not worldwide results' plus the desktop/English defaults clarify semantics not stated in the schema. It does not document the query length constraint, but that is minor.

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 (Read) and resource (compact Google search digest for one query) and enumerates exactly what it returns: organic results, feature names, cited domains, PAA questions. This clearly separates it from siblings like get_seo_backlinks, get_seo_keyword_metrics, and get_seo_page_audit, which target different SEO resources.

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?

Establishes scope with 'top-results digest, not a paginated complete search inventory' and clarifies no siteId is required so any brand/competitor can be researched. It gives strong context for when the tool is appropriate but does not name a specific alternative tool or the exact condition that would route the agent elsewhere.

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