Skip to main content
Glama
chrischall

zillow-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Compare multiple Zillow properties side-by-side

zillow_compare_properties
Read-onlyIdempotent

Compare 2-25 Zillow properties side by side using zpids or URLs, returning full records and an optional pivoted summary for analysis.

Instructions

Side-by-side analysis of 2-25 Zillow properties. If you just want N property records, use zillow_bulk_get instead — compare is for genuine side-by-side (its pivoted summary table is the value-add); bulk_get is the fetch-many endpoint and accepts up to 200 ids. (Issue #79 raised this cap from 8 to 25 — a 19-listing analysis now fits in one call instead of three.) Provide an array of zpids (or homedetails URLs). Returns the full per-property record per row (with extracted_features populated). Pass include_summary: true for an extra pivoted summary table (one row per field) — defaults off because results[].property.* already carries everything. The raw description is omitted from each row by default — pass include_description: true to keep it. Errors for individual properties are captured per-row — one bad zpid won't fail the whole call. Calls fan out concurrently (capped at 6 in flight, per issue #78, with retry-once-on-timeout per sub-request to absorb transient SW evictions), paced by the same throttle as zillow_bulk_get; a bot-wall block is retried with backoff and, if it persists, reported as error_kind: "bot_challenge" (distinct from a missing listing) with { blocked, retry_after_s } on the envelope. The call is bounded by an overall deadline — unsettled rows come back as error_kind: "pending".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlsNoArray of 2-25 Zillow homedetails URLs/paths to compare. Provide either zpids or urls, not both.
zpidsNoArray of 2-25 zpids to compare. Provide either zpids or urls, not both. For larger batches, use `zillow_bulk_get`.
include_summaryNoInclude the pivoted `summary` table (one row per compared field, one column per listing). Defaults to `false` because `results[].property.*` already carries everything — the summary roughly doubles response weight and is mainly useful for human-readable rendering.
include_descriptionNoInclude the raw `description` on each row. Defaults to `false`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.2.4
    • changedInput schema / properties / urls / description
      Previous value: -"Array of 2-25 Zillow homedetails URLs/paths to compare. Provide either zpids or urls."New value: +"Array of 2-25 Zillow homedetails URLs/paths to compare. Provide either zpids or urls, not both."
    • changedInput schema / properties / zpids / description
      Previous value: -"Array of 2-25 zpids to compare. Provide either zpids or urls. For larger batches, use `zillow_bulk_get`."New value: +"Array of 2-25 zpids to compare. Provide either zpids or urls, not both. For larger batches, use `zillow_bulk_get`."
    • changedInput schema / properties / zpids / items / anyOf
      Previous value: -[
-  {
-    "exclusiveMinimum": 0,
-    "maximum": 9007199254740991,
-    "type": "integer"
-  },
-  {
-    "type": "string"
-  }
-]New value: +[
+  {
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  {
+    "pattern": "^\\d+$",
+    "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

A4.8/5.0
Behavior5/5

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

Annotations declare read-only/idempotent/open-world, and the description adds substantial behavior beyond that: concurrency capped at 6 in flight, retry-once-on-timeout, shared throttling, per-row error capture (one bad zpid won't fail the call), bot-wall handling surfaced as error_kind 'bot_challenge' with {blocked, retry_after_s}, and an overall deadline yielding error_kind 'pending'. This is rich operational context consistent with the annotations (no contradiction).

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 critical routing distinction is front-loaded and bolded, and most sentences carry behavioral payload. It is long though, and the internal churn asides ('Issue #79 raised this cap from 8 to 25', 'per issue #78') are development noise an agent doesn't need, which slightly dilutes structure.

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 fully compensates: it describes rows (full per-property record with extracted_features), the optional pivoted summary table shape, per-row error envelope fields, and terminal error kinds. Nothing needed to interpret results 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 baseline is 3, but the description adds meaning beyond the schema: it explains why include_summary defaults off (results[].property.* already carries everything, and the summary roughly doubles response weight) and that include_description is omitted from rows by default. That rationale/payload-implication is genuine added value.

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 and resource with scope ('Side-by-side analysis of 2-25 Zillow properties') and explicitly differentiates itself from the sibling zillow_bulk_get. An agent can tell immediately which tool does the pivoted comparison vs. the plain fetch-many.

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?

Names the alternative explicitly and the condition that selects it: 'If you just want N property records, use zillow_bulk_get instead — compare is for genuine side-by-side... bulk_get accepts up to 200 ids.' This gives both when-to-use and when-not-to-use with the routing rationale.

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