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

Annotations only cover read-only and open-world behavior, and the description adds substantially beyond that: the data comes from carvana.com public inventory pages through a residential proxy, and each successful call costs $0.002 USDC via x402 on Base, Solana or Arc, with failed calls not charged. That billing/auth and sourcing detail is exactly the kind of context the annotations cannot convey.

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, the first front-loading what is returned and the paging limit, the second covering source and cost. It is dense but every clause carries information; the enumeration of returned fields is slightly redundant given an output schema exists.

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 three-parameter scraper with a full schema and output schema, the description covers source, paging limits, price model and billing protocol, which is close to everything an agent needs. It omits only edge behavior such as what happens when a make/model yields no listings or whether results reflect live inventory.

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 is 3, but the description adds the page density ('about 20 per page') and the 20-page ceiling, which the schema only states as a range. It also clarifies that trim is parsed from the listing text rather than being a query parameter, preventing a mis-filter assumption.

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 the specific resource and source: used-car listings from Carvana filtered by make and optional model. That implicitly distinguishes it from siblings like travel_carmax, travel_autonation and travel_autotrader, but it never says so explicitly, and the action verb (fetch/list) is only implied by the field list.

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?

Usage is implied by the make/model filter and the paging note, so an agent can infer it is for browsing Carvana inventory. There is no explicit guidance on when to choose this over the many other vehicle-listing siblings (carmax, autotrader, autonation, carsdirect) and no stated preconditions beyond the paid-call note.

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