search_cars

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

With no annotations, the description carries more burden, but it reveals a key behavior: some filtering happens in-memory from listing cards, implying results may be approximate and only from a single page/batch. It does not mention pagination depth, rate limits, or that in-memory filtering may require fetching many pages. It is honest about the mechanics but incomplete regarding scale and freshness.

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?

Three sentences, front-loaded with what the tool searches, then supported filters, then the in-memory caveat and return fields. No filler or redundancy.

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 search tool with 21 parameters and no output schema, the description communicates the main filtering domains and the return shape, which is a good foundation. However, with no output schema and no annotations, it would benefit from stating the listing card's data limitations (e.g., no full descriptions, images, dealer info), whether results are stale, and how page/limit interact with in-memory filtering. It is adequate but not exhaustive.

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 each parameter already has clear meaning. The description adds the important cross-cutting note that price/year/odometer filters are applied in-memory, which is not evident per-parameter. That is genuinely valuable. Baseline 3 is appropriate because the schema already documents parameters fully; the description adds a useful caveat but does not deeply describe interaction effects.

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 identifies a specific resource (carsales.com.au), a specific action (search), and enumerates the supported filter dimensions (make/model, state, body style, transmission, fuel type, condition, badge, keyword) plus what is returned. It clearly differentiates from siblings like search_facebook_cars and search_gumtree_cars by naming the source site.

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 explains what filters are available and that price/year/odometer are applied in-memory, so an agent understands mechanics. However, it does not explicitly say when to choose this over search_all_cars, get_listing_details, or watch_search, nor does it state whether this should be used for viewing vs. saving vehicles. No explicit exclusion criteria are given.

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