Skip to main content
Glama

Zillow MCP — Property Data, Zestimates & Listings for AI Agents

by com.zillapi
OverviewDiscussionsAdmin

Search U.S. property listings

search_listings

Search for-sale, for-rent, or sold listings inside a geographic bounding box, with optional bedroom and price-ceiling filters. Billed 1 credit per listing returned (up to max_items, default 50) — set max_items to cap the cost.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bboxYesGeographic bounding box as 'west,south,east,north' decimal lat/lon. Example: '-83.0,34.7,-82.0,35.0'.
statusYesListing status filter.
beds_minNoMinimum bedrooms (optional).
max_itemsNoMaximum listings to return, 1-50 (default 50). Billing is 1 credit per listing returned, so this caps your cost — e.g. max_items=5 costs at most 5 credits. Omit for the default 50.
price_maxNoPrice ceiling in USD (optional).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / max_items
      Added value: +{
+  "description": "Maximum listings to return, 1-50 (default 50). Billing is 1 credit per listing returned, so this caps your cost — e.g. max_items=5 costs at most 5 credits. Omit for the default 50.",
+  "type": "integer"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It goes beyond the norm by exposing a concrete cost model (1 credit per listing returned, capped by max_items, default 50), which is genuinely useful. It does not cover return format or error behavior, but those are less critical for a non-destructive search.

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

Conciseness5/5

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

Two tight sentences with no filler; the primary search purpose is front-loaded ahead of the cost caveat. Every clause earns its place.

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?

Purpose, parameters, and cost are fully covered, but with no output schema the description does not state what a result entry looks like or how results are ordered/paginated — a genuine gap for an agent that must consume the returned listings.

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% — every parameter, including bbox with an example and max_items with the default and cost-cap note, is documented. The description adds the billing/cost-capping context, but that is largely duplicated in the schema's own max_items description, so marginal added value over 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?

The description names a specific verb (search) and resource (listings), and narrows scope with status types (for-sale/for-rent/sold) and a geographic bounding box. This area-based multi-result search is clearly distinguishable from the sibling lookup tools (single-property by address/zpid, zestimate), even though siblings are not named explicitly.

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

Usage Guidelines3/5

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

The intended use — finding many listings inside a region — is implied by the purpose statement, but there is no explicit guidance on when to prefer this over the sibling lookup tools, nor any exclusions or routing hints. Selection is left to inference.

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

All Zillow MCP — Property Data, Zestimates & Listings for AI Agents toolsInspect
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