get_dealer_ratings

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It states that the tool includes 'per-review rating, text, dealer reply and paging totals', which informs the agent of the response contents and that it supports paging (via 'paging totals'). It implicitly indicates a read operation ('Fetch') and does not mention any destructive or state-changing behavior. It does not explicitly state authentication or rate limits, but for a simple fetch with pagination, the disclosure is adequate.

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 a single, well-structured sentence that front-loads the verb and resource ('Fetch a dealer's customer reviews'), then immediately clarifies the critical ID source and lists response contents. It is concise with zero wasted words, and the clarification is placed early to prevent misuse. The structure is efficient and informative.

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 three parameters and no output schema, the description provides a solid overview: it states the purpose, the required ID and its source, and the key fields returned (rating, text, dealer reply, paging totals). It also mentions paging, which aligns with the size/offset parameters. It does not detail the exact response structure (e.g., is it a list of objects?), but given the listing of contents, an agent can reasonably infer the return format. Minor gaps like error handling or edge cases are not critical for a fetch operation.

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 100%, so the input schema already documents all three parameters (dealerId, size, offset) with descriptions. The tool description adds context about dealerId's origin ('from get_watch's sellerIds'), but this is already present in the schema description ('Dealer id from get_watch's sellerIds (NOT the customerId)'). The description does not add new semantic value for parameters beyond what the schema provides, so baseline 3 applies.

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 clearly states the action ('Fetch a dealer's customer reviews') and specifies the key identifier (dealerId) with a crucial disambiguation: it's from get_watch's sellerIds, not the customerId. This distinguishes it from other tools that might use similar IDs, and the mention of 'dealer ratings' implies the resource. It stands apart from siblings like get_dealer_listings or get_watch by focusing on reviews/ratings.

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 provides clear context on the correct source of the dealerId ('from get_watch's sellerIds - NOT the customerId'), which guides correct usage and prevents common misuse. It does not explicitly name alternative tools or state when not to use this tool, but the context about the ID source is a strong usage guideline. It implies usage for fetching reviews, and the clarification about ID origin is a form of usage guidance.

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