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

Annotations already declare this a read-only, open-world call, so safety is covered. The description adds real behavioral context beyond that: the 10-100 depth range, the fact that local pack and shopping are opt-in add-ons rather than defaults, and a cache-vs-live tradeoff where fresh=true costs more. It stops short of stating rate limits, latency, or failure modes.

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?

Four sentences, front-loaded with the core action and scope, then the add-on flags, then the cache tradeoff. Dense but each sentence carries distinct information; only the classification-tagging enumeration is arguably decorative.

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 correctly spends words on return composition (organic results plus page features like AI Overview, PAA, Knowledge Graph), which is exactly what an agent needs. The gap is the undocumented gl/hl/location parameters and the absence of routing against siblings that fetch local or shopping data directly.

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 description coverage is 0%, so the schema contributes only titles and defaults; the description must carry the load. It explains query, depth, fresh, local_pack and shopping semantics well but says nothing about gl, hl, or location, leaving three geo/locale parameters with no meaning assigned anywhere.

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?

The description states a specific verb+resource ('Execute a full Google SERP search query') and a concrete scope constraint (depth 10 to 100). It also enumerates what comes back (organic results, classification tags, page features), so an agent knows exactly what this tool produces. It does not, however, name or differentiate itself from close siblings like ai_answers, extract_local_places, or extract_shopping_results, which cover overlapping surface area.

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?

It gives per-flag usage guidance (set local_pack and/or shopping to include those blocks; set fresh to true to search live instead of using the 24-hour cache), which is genuinely actionable. What is missing is tool-level routing: nothing says when to choose google_serp over ai_answers or extract_local_places, so the agent must infer that from the siblings' own descriptions.

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