Hercules property data

Quote a national property search

quote_national_property_search

Read-onlyIdempotent

Quotes a search of national property data: any US property, including NYC properties that are not in preforeclosure. Filters: place (state plus zip, city or county), property type, beds, baths, value, equity, year built, distress flags (preforeclosure, foreclosure, auction, bank-owned, vacant, absentee owner, high equity, free and clear, inherited) and owner filters (company-owned, out-of-state owner, cash buyer, owners of N+ properties, last sale dates). Never spends credits: it counts the matches and prices one batch. Always quote first. Then tell the user the credit cost, the batch size and their balance after. Records this workspace already pulled in the last 24 hours are free. For large searches, prefer a smaller batch (limit) or narrower filters, such as a zip instead of a county. One run returns at most 250 records; page with offset. Quotes expire after 10 minutes. Call run_national_property_search with the quote_id only after the user agrees to the credit cost.

Input Schema

Name	Required	Description
`zip`	No	Five-digit zip code. The narrowest and cheapest place filter.
`city`	No	City name.
`flags`	No	Only properties with all of these: pre_foreclosure, foreclosure, auction, reo (bank-owned), vacant, absentee_owner, high_equity, free_clear (no mortgage), inherited, death (owner deceased, a probate signal), judgment (judgment lien), tax_lien, mls_cancelled (listing cancelled or expired, a failed sale), negative_equity.
`limit`	No	Records to price in this batch (max 250). Leave empty to let the quote pick a safe batch size.
`state`	Yes	Two-letter state code, e.g. TX. Required.
`county`	No	County name, without the word County.
`offset`	No	Skip this many matches. Use it to quote the next page.
`bedsMin`	No
`bathsMin`	No
`valueMax`	No
`valueMin`	No
`cashBuyer`	No	Only properties bought with cash.
`propertyType`	No	SFR single family, MFR multifamily, CONDO, LAND, MOBILE or OTHER.
`yearBuiltMax`	No
`yearBuiltMin`	No
`lastSoldAfter`	No	Last sale on or after this date.
`corporateOwned`	No	Only properties owned by a company or LLC.
`lastSoldBefore`	No	Last sale on or before this date.
`outOfStateOwner`	No	Only owners whose mailing address is in another state.
`equityPercentMin`	No	Minimum estimated equity, in percent.
`ownerPropertiesMin`	No	Only owners who own at least this many properties.

Output Schema

Name	Required	Description	Default
`offset`	Yes
`balance`	Yes
`credits`	Yes
`quoteId`	Yes
`runTool`	Yes
`expiresAt`	Yes
`affordable`	Yes
`suggestions`	Yes
`balanceAfter`	Yes
`ownedInBatch`	Yes
`totalMatches`	Yes
`recommendation`	Yes
`recordsInBatch`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 18, 2026

changedInput schema / properties / flags / description

Previous value: -"Only properties with all of these: pre_foreclosure, foreclosure, auction, reo (bank-owned), vacant, absentee_owner, high_equity, free_clear (no mortgage), inherited."New value: +"Only properties with all of these: pre_foreclosure, foreclosure, auction, reo (bank-owned), vacant, absentee_owner, high_equity, free_clear (no mortgage), inherited, death (owner deceased, a probate signal), judgment (judgment lien), tax_lien, mls_cancelled (listing cancelled or expired, a failed sale), negative_equity."

changedInput schema / properties / flags / items / enum

Previous value: -[
-  "pre_foreclosure",
-  "foreclosure",
-  "auction",
-  "reo",
-  "vacant",
-  "absentee_owner",
-  "high_equity",
-  "free_clear",
-  "inherited"
-]New value: +[
+  "pre_foreclosure",
+  "foreclosure",
+  "auction",
+  "reo",
+  "vacant",
+  "absentee_owner",
+  "high_equity",
+  "free_clear",
+  "inherited",
+  "death",
+  "judgment",
+  "tax_lien",
+  "mls_cancelled",
+  "negative_equity"
+]

changedInput schema / properties / flags / maxItems
```
Previous value: -9New value: +14
```

First observedOct 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare the read-only/idempotent safety profile; the description goes well beyond by disclosing cost behavior (never spends credits, counts matches, prices one batch), free 24-hour records, the 250-record cap, offset paging, and a 10-minute quote expiry. These are the traits an agent cannot infer from readOnlyHint alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then cost/workflow, then paging and expiry constraints – each sentence carries a distinct operational instruction. It is dense but not padded; the only minor cost is a long single-paragraph run of instructions that could be split for scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 21-parameter quoting tool with an output schema, the description supplies everything an agent needs to call it correctly: required state, filter scope, batch sizing, pagination, quote lifetime, and the handoff to run_national_property_search. Return-value explanation is correctly omitted since an output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 71% and the description enumerates filter categories (place, type, beds, baths, value, equity, year built, flags, owner filters) that map to the parameters. However, it adds no syntax or semantics for the undocumented params such as bedsMin, bathsMin, valueMin/valueMax and yearBuiltMin/Max, so it neither compensates fully nor exceeds the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (quotes) plus the resource (a search of national property data), and scopes it against siblings by naming NYC preforeclosure exclusions and, later, run_national_property_search as the follow-up. An agent can tell it apart from quote_active_investor_search, quote_investor_firm_search and quote_llc_owner_lookup without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit sequencing: 'Always quote first. Then tell the user the credit cost... Call run_national_property_search with the quote_id only after the user agrees.' It also names a fallback strategy (smaller batch or narrower filters, zip instead of county) for large searches. When, when-not, and the alternative tool are all stated.

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

All Hercules property data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?