search_cars

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

No annotations are provided, so the description carries the burden. It discloses that this searches a 'local historical database' (implying offline, collected data) and mentions pagination. However, it doesn't disclose return format, default behavior when no filters are given, or whether results are sorted by relevance vs. newest. The description adds some context but leaves significant behavioral details to the output schema.

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?

A single, dense sentence that front-loads the core purpose ('Search the local historical database of collected listings') and then summarizes capabilities. Every word earns its place; no fluff or repetition of schema details.

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 34-parameter tool with no annotations, the description is minimal. The output schema exists, so return values are covered, and the schema documents many parameters. However, the description doesn't clarify key behavioral aspects like whether this is a read-only operation, how pagination interacts with sorting, or what 'historical' means in terms of data freshness. It's adequate but leaves gaps for a complex tool.

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 53%, so the schema documents many parameters. The description adds the high-level concept of 'rich filters, geography and pagination' but doesn't explain any specific parameter semantics beyond what the schema already provides. With 34 parameters and 53% coverage, the description could have compensated for the undocumented half, but it doesn't. 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?

The description states a specific verb ('Search'), a specific resource ('local historical database of collected listings'), and the key capabilities ('rich filters, geography and pagination'). It clearly distinguishes this from the sibling search_live_marketplace by emphasizing 'local historical database' vs. live marketplace. An agent can tell this is the offline/historical search tool without opening the 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?

The description implies this is the tool for searching collected/historical listings, which contrasts with search_live_marketplace. However, it doesn't explicitly state when to use this vs. alternatives like get_new_listings, find_deals, or find_price_drops. The 'local historical database' phrasing gives clear context but no explicit exclusions or alternative routing.

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