Skip to main content
Glama

Search properties (deprecated)

spur_search_properties
Destructive

DEPRECATED: use spur_parse_data_search to preview and spur_data_search to run searches. This tool stays for existing prompts and the property explorer cards, and now runs on Data Search: the same filters, mapped by Spur, with each value labeled by its provider.

listing_status (forRent / forSale / sold) searches current listings on ZHomes; without it the search covers off-market and owner records with automatic provider routing. Costs 1 search credit plus data credits per record returned (limit caps it); an empty page is free. Listing event filters (price drops, back on market, ...) are not available here: use spur_create_search_automation for those.

Follow up with spur_save_properties (pass the cards' listing objects) or spur_save_data_results. Saving is free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "confirm": "<confirm>"
    },
    "name": "spur_search_properties"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum results (also caps the credits charged)
queryNoFree-text request; Spur turns it into filters
viewsNoOnly listings with any of these view types
eventsNoOnly listings where any of these events happened; see the tool description
confirmYesSet to true ONLY after the user explicitly approved this exact action in the conversation. Never assume approval.
max_ageNoAt most this many years since built
max_zipNoHighest ZIP code in a numeric ZIP range (with min_zip)
min_ageNoYears since built
min_zipNoLowest ZIP code in a numeric ZIP range (with max_zip); prefer zip_list for specific ZIPs
has_poolNotrue = only listings with a pool
has_viewNotrue = only listings with any view (use views on live search for a specific kind)
keywordsNoComma-separated listing keywords, e.g. "pool, granite"
locationNoCity and state ("Dallas, TX") or ZIP code
max_bedsNoMaximum bedrooms
max_sqftNoMaximum living area in square feet
min_bedsNoMinimum bedrooms
min_sqftNoMinimum living area in square feet
zip_listNoKeep only these ZIPs; set location to the city that contains them
home_typeNoZillow home type code
max_bathsNoMaximum bathrooms
max_priceNoMaximum price (monthly rent for rentals), USD
min_bathsNoMinimum bathrooms (half baths count as 0.5)
min_priceNoMinimum price (monthly rent for rentals), USD
center_latNoRadius search centre (with center_lng and radius_miles)
center_lngNoRadius search centre longitude (with center_lat and radius_miles)
has_garageNotrue = only listings with a garage
min_equityNoEstimated equity in USD (Zestimate or price minus assessed value; rough)
days_postedNoOnly listings posted within this many days
has_3d_tourNotrue = only listings with a 3D virtual tour
only_vacantNoLikely vacant (heuristic: description keywords + long days on market)
listing_typeNoSeller / listing kind; for catching NEW entries into a distress stage prefer events
max_lot_sizeNoSquare feet
min_lot_sizeNoSquare feet (1 acre = 43,560)
radius_milesNoKeep only listings within this many miles of center_lat / center_lng
is_waterfrontNotrue = only waterfront listings
neighborhoodsNoNeighborhood / area names matched against address and description
only_absenteeNoAbsentee-owned (owner mails elsewhere)
has_open_houseNotrue = only listings with an upcoming open house
listing_statusNoSet for a listing search; omit for off-market and owner records
max_year_builtNoBuilt in or before this year
min_year_builtNoBuilt in or after this year
ownership_typeNobusiness = LLC / corp / trust owners (heuristic)
is_single_storyNotrue = only single-story homes
event_stale_daysNoDays on market that counts as stale (default 90)
is_price_reducedNotrue = only listings whose asking price has been cut
event_within_daysNoLookback window for events, in days (default 7)
max_days_on_marketNoListed at most this many days
min_days_on_marketNoListed at least this many days (higher suggests a motivated seller)
max_ownership_yearsNoOwner has held the property at most this long
min_ownership_yearsNoOwner has held the property at least this long
event_min_change_pctNoMinimum % move for price / rent / Zestimate / assessment events
has_air_conditioningNotrue = only listings with air conditioning
only_pre_foreclosureNoDistressed / pre-foreclosure (heuristic, includes description keywords)
event_min_equity_gap_pctNoMinimum % Zestimate above last sale price for equity_gap (default 30)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / confirm
      Added value: +{
      +  "const": true,
      +  "description": "Set to true ONLY after the user explicitly approved this exact action in the conversation. Never assume approval.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum results to show"New value: +"Maximum results (also caps the credits charged)"
    • changedInput schema / properties / listing_status / description
      Previous value: -"Defaults to forRent when omitted and the query doesn't imply one"New value: +"Set for a listing search; omit for off-market and owner records"
    • changedInput schema / properties / query / description
      Previous value: -"Free-text intent; Spur's AI turns it into filters and re-ranks by description"New value: +"Free-text request; Spur turns it into filters"
    • addedInput schema / required
      Added value: +[
      +  "confirm"
      +]
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare openWorld/destructive/non-idempotent, and the description adds genuinely new behavior: provider routing for off-market records, per-record data credit charges capped by limit, free empty pages, and free saving. What is missing is any explanation of how results are returned (page shape, pagination) and why a search carries destructiveHint=true.

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?

The deprecation notice is correctly front-loaded and most sentences carry real information (costs, status semantics, follow-ups). The layout is choppy — mid-paragraph line breaks split the status and cost rules from the routing note — which slightly hurts scanability for a 54-parameter tool.

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

Completeness3/5

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

Given 54 parameters, no output schema, and no nesting, the description covers cost and routing but says nothing about result shape, pagination, or how the many filter axes interact (events versus listing_status, age versus year_built). An agent can invoke it, but not confidently predict what it returns.

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 coverage is 100%, so the baseline is 3 and the listing_status explanation is a real addition. However, the description says listing event filters 'are not available here' while the schema exposes a full events enum array that even points back to the description for guidance — a direct conflict that leaves the agent unsure whether events work.

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 concrete verb and resource (search properties) and immediately frames it as the legacy entry point now backed by Data Search. It explicitly distinguishes itself from spur_parse_data_search and spur_data_search, so an agent can route correctly without opening sibling schemas.

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 routing rules: preview with spur_parse_data_search, run with spur_data_search, keep this only for existing prompts and property explorer cards. It also says when to include listing_status versus omitting it, and redirects listing-event filtering to spur_create_search_automation.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources