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

Annotations only declare readOnlyHint and openWorldHint, but the description adds several behavioral facts an agent could not infer: results are 24 per page with a total count, pre-foreclosure data is mostly withheld from anonymous visitors, billing is $0.002 USDC per successful call via x402 across three chains, and failed calls are not charged. The withholding caveat and the pay-per-success rule are exactly the kind of operational context that changes invocation decisions.

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?

Purpose is front-loaded and the caveat/pricing follow in a logical order. The long semicolon-chained field inventory is somewhat redundant given an output schema exists, and the immowelt clause ends in a garbled fragment ('for a city: per'), which is wasted or confusing text. Overall still tight for the amount of useful information conveyed.

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 an open-world, paid, paginated scraping tool this covers everything an agent needs: geographic scope, pagination size, a data-availability trap, cost model, and sibling routing, on top of a full output schema. Nothing material about invoking it correctly 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 coverage is 100%, so the baseline is 3, and the description does add meaning beyond it: it explains that the status filter's pre-foreclosure value typically yields empty results, which the schema presents neutrally as a valid option. It also ties zip to the city+state requirement. It does not add anything about page iteration beyond what the schema states.

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+resource+scope: RealtyTrac foreclosure listings for a US city or ZIP, then enumerates the record shape (REO/auction, address, county, beds/baths, sqft, estimated value, ROI, auction partner/date, status, coordinates, listing URL). It explicitly names what it is not by pointing at realestate_immowelt (Germany) and realestate_loopnet (commercial US), so an agent can separate it from the many real-estate siblings without opening a 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?

Gives clear context for when to call it (US city/ZIP foreclosure and REO data) and routes to two named alternatives for different needs. It also warns that the pre-foreclosure filter often returns nothing for anonymous visitors, which is genuine when-not guidance. It does not, however, differentiate itself from other US residential listing siblings like realestate_zillow or realestate_redfin_property_listings.

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