Skip to main content
Glama
chrischall

zillow-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Exhaustively sweep a Zillow search area

zillow_sweep_area
Idempotent

Enumerate every Zillow listing in a location or bounding box without silent truncation by splitting the area into map tiles, recursively quartering crowded tiles, and deduping results.

Instructions

Enumerate EVERY Zillow listing matching the filters inside a location (resolved like zillow_search_properties) or an explicit bounding box, without silent truncation. Splits the area into map tiles and recursively quarters any tile whose Zillow-reported total exceeds what one query can return, dedupes by zpid and re-applies the numeric filters (drift guard). Returns a completeness summary (requests, tiles, unique listings, tiles still truncated at max depth, drift warnings such as Zillow ignoring the price filter or the viewport) plus the listings, or writes the listings to output_path as JSON for large areas. Sequential requests with a delay. Read-only against Zillow; the only write is the optional local output file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
boundsNoOptional box to sweep; defaults to the resolved region's map bounds.
statusNo
beds_minNo
delay_msNoPause before every Zillow request, including each page within a tile (default 1200).
locationYesCity / ZIP / county used to resolve the region (e.g. "King County, WA").
tile_capNoTreat a tile as complete only if its total is at most this (default 400).
baths_minNo
max_depthNoMax quarterings per tile (default 6).
price_maxNo
price_minNo
home_typesNo
output_pathNoOptional absolute path of a NEW .json file to write the full results (and per-tile counts) to; an existing file is never overwritten. Omit to get the results inline; use a file for large areas so the listings stay out of the conversation.
max_requestsNoHard request budget (default 150), counting the resolve call and every page; the sweep stops mid-tile rather than exceed it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Discloses behavior far beyond the annotations: recursive tile quartering, dedupe by zpid, re-application of numeric filters as a drift guard, sequential throttled requests, and the completeness/warning summary returned. Critically, it explains why readOnlyHint=false is not dangerous ('Read-only against Zillow; the only write is the optional local output file'), removing ambiguity an agent would otherwise face.

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 core guarantee (no silent truncation) is front-loaded in the first clause, then mechanism, then return shape. Dense but nearly every clause carries distinct information; the multi-clause first sentence is long but not padded.

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 complex, nested-schema, 13-param tool with no output schema and an unconventional readOnlyHint=false, the description covers mechanism, throttling, write behavior (new file, never overwritten), and the shape of the returned summary, which is exactly what an agent needs to call it correctly.

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

Parameters4/5

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

With 54% schema coverage and 13 params, the description compensates by explaining the intent of the algorithm-level knobs (tile_cap, max_depth, max_requests as a 'hard request budget' that stops mid-tile, bounds defaulting to resolved region bounds). The plain filter params (status, beds_min, price_min/max, home_types) remain undocumented in both places, but they are conventionally named.

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 ('enumerate EVERY listing'), resource (Zillow search area), and the distinguishing property versus the sibling search tool: exhaustive tiling without silent truncation. 'Resolved like zillow_search_properties' explicitly positions it relative to that sibling, so an agent can choose between them without opening schemas.

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

Usage Guidelines4/5

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

Gives clear context for use (large areas where a single query truncates) and routes large results to output_path 'so the listings stay out of the conversation'. It stops short of an explicit when-not-to-use rule (e.g. 'for a quick single-page lookup use zillow_search_properties'), leaving that inference to the agent.

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

Deploy Server

Other Tools