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

With readOnlyHint/openWorldHint already covering the safety profile, the description adds genuinely non-obvious behavior: it shares the /search anti-bot gate, a blocked attempt returns `upstream_blocked` and is not charged, and each call costs 5 credits. That billing and failure-mode disclosure is exactly what annotations cannot express. It doesn't cover pagination behavior for `start`, which keeps it from a 5.

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 short sentences, front-loaded with what the tool returns before the operational caveats. Minor waste: 'Google Shopping results.' and 'Shopping tiles for a query' say nearly the same thing, and 'google.search already documents' forces a cross-tool lookup.

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 naming the returned tile fields is the right compensation, and cost plus the `upstream_blocked` failure mode round out what an agent needs before calling. For a read-only search tool with 89% schema coverage, nothing essential is missing.

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 89%, so the schema already documents gl, hl, tbs, tld, uule, query and start — baseline 3 applies. The description adds no parameter-level detail beyond naming the output fields, and the one undocumented parameter (`cache_max_age`, no schema description) is left entirely unexplained.

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 the resource (Google Shopping results for a query) and enumerates the returned fields — title, price, currency, merchant — which lets an agent distinguish it from web-search siblings like google_search or google_news. It stops short of explicitly naming the alternative, so it is clear but not sibling-differentiated at the level of a 5.

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?

There is no when-to-use guidance at all: nothing tells the agent to pick this over google_search, amazon_search, ebay_search, or walmart_search for a product query, nor whether it is for price comparison versus product detail. The only conditional content is about failure handling, not tool selection.

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