google_shopping

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and behavior. The description adds context about error conditions (missing API key, rate limit, request failure) and the output format (JSON/CSV). It does not fully detail pagination behavior beyond param hints, but overall it supplements the annotations well without contradiction.

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?

The description is concise with three paragraphs, a returns clause, and a raises clause. It is front-loaded with the core purpose and structured with clear sections (when to use, when not to use, args, returns). No extraneous information.

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?

Given the tool's complexity (shopping search with multiple siblings), the description fully covers its role, distinguishes it from alternatives, explains typical use cases, and notes error conditions. It references an output schema, so no further detail on return values is needed. The description is self-contained for an AI agent to decide when and how to invoke it.

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% (the description does not repeat parameter details), but the schema itself has detailed descriptions for each parameter. The tool description refers to params by category (localization, pagination, etc.), which adds organizational value. Since the schema already provides full parameter semantics, the description's summary is sufficient and adds clarity.

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 uses a specific verb ('Retrieve parsed Google Shopping product results') and clearly identifies the resource ('for a query'). It lists the structured fields returned (product title, price, merchant, rating, link) and explicitly distinguishes from sibling marketplace tools (Amazon, Walmart, eBay) and general web search, making the purpose unambiguous.

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?

The description includes explicit 'When to use' (price comparison, market research) and 'When NOT to use' sections, naming specific alternatives like amazon_search, walmart_search, and google_search. This provides clear decision criteria for the agent.

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