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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile (non-mutating, live web retrieval) is covered structurally. The description adds a useful return-field inventory, which is meaningful given no output schema, but says nothing about rate limits, pagination, or failure behavior.

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?

Two sentences with no filler, and the purpose is front-loaded ahead of the return inventory. Efficient, though the second sentence is a flat field dump rather than structured guidance.

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 return-field list does useful work in describing what comes back. But for a 5-parameter tool with 0% schema coverage, the total omission of parameter meaning leaves the definition incomplete 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?

Five parameters with 0% schema description coverage and zero enum constraints, yet the description never mentions gl, hl, fresh, or location. The geolocation, language, and freshness controls are entirely undocumented in both schema and prose, a real gap for a tool whose results are locale-dependent.

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?

Specific verb+resource: 'Extract Google Shopping carousel listings' clearly states what is retrieved and scopes it to 'e-commerce and product queries'. It is distinguishable from siblings like google_serp or extract_local_places by the Shopping carousel framing, though it never names or contrasts those siblings.

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?

'For e-commerce and product queries' implies the domain in which this tool applies, giving usable context. However, it offers no explicit when-not guidance or alternatives (e.g., use google_serp for organic results, extract_local_places for local listings), leaving routing to inference.

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