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

Annotations only give the generic write/open-world/non-idempotent profile; the description adds substantial behavior: VIN/plate decoding, a rule-based estimate, multi-language copy generation, rate limits per client and per day, and the fact that a public listing page goes live on autoprivado.com. It also flags the secret edit URL as seller-only, which is a disclosure rule an agent could not infer from annotations.

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 action and eligibility constraint, then capabilities, then outputs and limits, so an agent can stop reading early. It is a single dense paragraph with some enumeration that could be better structured, but no sentence is filler.

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 21-parameter write tool with a nested vehicle object and no output schema, the description covers the return values (listing URL plus secret edit URL), the post-creation workflow (posting kits), and rate limits. The gap is per-field meaning for the optional details, which is the only thing an agent could still get wrong.

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?

At 62% schema coverage the schema already documents the key inputs (vin, plate, price, alsoIn, newPrice, contact), and the description adds interpretive context by naming what vin/plate trigger (NHTSA/RDW lookup) and how price estimation works. However, it never explains the many structural/condition parameters (city, colour, owners, gearbox, condition, vehicle overrides) beyond what the schema already states, so it does not compensate for the remaining coverage gap.

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 ('Create a car-for-sale listing') plus the exact scope: private seller, AutoPrivado, only with owner consent. Siblings are all read/decode/estimate tools, so the create-vs-retrieve distinction is unambiguous from the description alone.

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?

Clearly defines the eligible context (private seller, owner consent) and rules out an expectation the agent might otherwise have: AutoPrivado never posts to portals, the seller does it via the posting kit. It does not explicitly contrast with decode_vehicle or estimate_price, which are the obvious alternative paths if the agent only wants a lookup rather than a live listing.

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