Skip to main content
Glama
Sign In
zillow-mcp

zillow-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Get my saved Zillow searches

zillow_get_saved_searches
Read-onlyIdempotent

Retrieve a signed-in user's saved Zillow searches, including filters, new-listing counts, and notification frequency, to check for new listings. Requires an authenticated Zillow browser session.

Instructions

The signed-in user's saved searches on zillow.com (name, filters, new-listing count, notification frequency) — the answer to "anything new on my saved searches?". view: 'brief' gives one line per search with its new-listing count. Requires the user to be signed in at zillow.com in the bridged browser tab — throws SessionNotAuthenticatedError otherwise. An optional session_id (from zillow_register_session) is checked against the session registry — an unknown id errors — but it is a label only: the request always goes through whichever browser tab the extension is signed into. Read-only; safe to call repeatedly.

Input Schema

NameRequiredDescriptionDefault
viewNo"full" (default) returns each saved search as JSON; "brief" returns one line per search: name — <last update as an ISO date, or "no date"> — <N new | no new listings | new count unknown> ("new count unknown" when Zillow omits the count for that search); no saved searches answers the single note line "-- none".
session_idNoOptional registered session id (from `zillow_register_session`). Defaults to the active session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.3.1
    • addedInput schema / properties / view
      Added value: +{
+  "description": "\"full\" (default) returns each saved search as JSON; \"brief\" returns one line per search: name — <last update as an ISO date, or \"no date\"> — <N new | no new listings | new count unknown> (\"new count unknown\" when Zillow omits the count for that search); no saved searches answers the single note line \"-- none\".",
+  "enum": [
+    "full",
+    "brief"
+  ],
+  "type": "string"
+}
  2. Changed1 schema field changedv1.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observedv0.11.1

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the sign-in prerequisite, the specific SessionNotAuthenticatedError failure, that an unknown session_id errors, and that session_id is a label only since the request always goes through whatever tab the extension is signed into. This is exactly the non-obvious auth/routing behavior an agent needs before calling.

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-loads the resource and the payoff question, then prerequisites, then parameter caveats — a sensible order in one dense paragraph. It loses little, though 'Read-only; safe to call repeatedly' duplicates the readOnlyHint/idempotentHint annotations rather than adding information.

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?

With no output schema, the description carries the return burden and does it: it names the fields returned in full mode and the exact line format in brief mode, including the '-- none' empty case. Combined with the auth and session caveats, nothing needed to call this correctly is missing.

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?

Schema coverage is 100%, so the baseline is 3; the description earns an extra point for explaining that an unknown session_id errors and that the id does not actually select a tab. Its `view: 'brief'` summary largely restates the very detailed schema description of that parameter.

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+resource (retrieve the signed-in user's saved searches) and enumerates the fields returned (name, filters, new-listing count, notification frequency). Names the user question it answers, and 'saved searches' is unambiguous against siblings like zillow_get_saved_homes or zillow_search_properties.

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 when-to-use framing ('anything new on my saved searches?') and conditions the `view: 'brief'` mode on wanting one line per search. It does not explicitly exclude or route to the nearest alternative (zillow_get_saved_homes for saved homes), so it falls short of full when-not guidance.

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