export_csv

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

With no annotations provided, the description carries the full behavioral burden. It does disclose meaningful traits: the operation is free, requires no external service, and returns the CSV as a text block rather than a file artifact. It does not disclose limits on CSV size, whether a live search is executed, or any auth requirements, but the core side-effect and return-format behavior are stated.

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?

Two sentences with zero waste: the first front-loads the action, cost profile, and use case; the second states the return format. Every clause earns its place, and the most decision-relevant facts (free, no external service, output is a text block) appear first.

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?

The description compensates for the missing output schema by stating the return value is a CSV text block, and the input schema covers all 10 parameters. The main gaps are the ambiguous relationship to the search tools (does it run its own search or export existing results?) and no mention of result volume truncation or delivery size limits. Adequate but not fully self-contained.

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 baseline applies. The description adds no parameter-specific detail beyond what the schema already provides, but none is needed — each parameter (make, limit, minPrice, state, etc.) is already documented clearly. The phrase 'a carsales search' does loosely tie the params together as search filters.

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 names a specific verb ('Export'), a specific resource ('a carsales search'), and a concrete output format ('CSV'), plus the practical benefit ('opened in a spreadsheet'). It is immediately distinguishable from all siblings, which are search, offer, watch, or auth tools — none of which do CSV export.

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 gives the use case ('so results can be opened in a spreadsheet') and differentiates the approach ('free, no external service'), which implies when an agent would reach for this tool. However, it does not explicitly explain the relationship to search_cars or search_all_cars — whether this runs a fresh search with the given filter params or exports previously fetched results — and names no alternatives or exclusions.

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