Dealers selling a model

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely new behavioral context: it scans only the first pages of dealer-only ads, dealer ids and names are derived from ads rather than a canonical dealer directory, and each dealer's own listing is at the returned url — an important provenance and coverage caveat that the annotations cannot express.

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 the resource and return fields, then use-case, then follow-up call — a sensible ordering with no filler. The second paragraph is slightly run-on ('dealer ids and names come from the ads, and each dealer's own listing is at the returned url'), but every clause carries 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?

For a read-only discovery tool with no output schema, the description still tells the agent what comes back (address, rating, matching ad count, url), how complete the scan is, and which tool to chain into. Nothing needed to call or interpret it is missing.

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 schema already explains pages, region and vehicle in detail. The description only echoes the 'model or city' axis and does not add format or interaction details (e.g. how region and vehicle combine, or that pages bounds runtime). Baseline 3 is appropriate.

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?

States a specific verb and resource ('List car dealers (showrooms) with ads for a model or city') plus the returned fields (address, rating, matching ad count). This clearly separates it from sibling ba_dealer_ads (ads of one dealer) and ba_search (general ad search).

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?

Gives an explicit use-case phrasing ('where can I buy X from a dealer') and then routes the agent onward: 'call ba_search with seller=dealer for the ads themselves.' Both the when-to-use and the alternative are named, so nothing is left to inference.

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