Search car ads

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, yet the description still adds non-obvious behavior: 30 ads per page, the site exposes no total count, and the agent must keep paging while has_more is true. It also discloses data conventions the agent cannot infer — prices in Toman, Jalali years with possible Gregorian imports, mileage 0 meaning zero-km — plus the workaround that ba_ad reports the true count for one model.

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?

Front-loaded with purpose and result shape, then workflow, then paging caveat — every sentence carries operational information and none is filler. It loses a point for density and a broken clause ("region, body, fuel and" trailing into a new line) that makes the value-sourcing sentence harder to parse than it needs to be.

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 26-parameter, zero-required search tool with no output schema, the definition covers pagination, result size, units, and cross-tool value sourcing, which is what an agent needs to call it correctly. The remaining gap is minor: it never enumerates the fields of a "compact ad" or explains that the returned `code` is the handle for ba_ad, though the ba_ad reference implies 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?

With 92% schema description coverage the schema already carries most parameter meaning, including the ba_filters kind references and Toman/Jalali units. The description's parameter content (Toman pricing, Jalali years, the zero-mileage convention, value sourcing from ba_vehicles/ba_filters) largely restates what the schema says, adding little syntax or format detail beyond it. Baseline 3 is appropriate given the schema does the heavy lifting.

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?

"Search used and new car ads on Bama (bama.ir) with filters; returns up to 30 compact ads per page" gives a specific verb, resource, domain, and result shape. It actively carves out the sibling boundary by naming ba_search_bikes_trucks for motorcycles/trucks, so an agent can route without opening another schema.

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?

Explicit when-to-use ("find me X under Y" questions), explicit prerequisite workflow (fetch brand/model from ba_vehicles, region/body/fuel/color from ba_filters), and explicit next steps (ba_ad for full details, ba_market_stats for statistics). It also names the exclusion case — motorcycles and trucks go to ba_search_bikes_trucks — which is exactly the routing information an agent needs.

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