Skip to main content
Glama
chrischall

homes-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Compare homes.com properties side-by-side

homes_compare_properties
Read-onlyIdempotent

Compare 2-8 homes.com property URLs side-by-side, aligning key facts like price, HOA fees, days on market, and lot size. Captures errors per listing, so one bad link won't break the comparison.

Instructions

Fetch 2 or more homes.com properties and align their facts side-by-side. Each target supplies a url — the full homes.com property URL (e.g. from a homes_search_properties result's url field). Returns the full per-property record (with server-side extracted_features, hoa_monthly_usd, days_on_market, price_drop_*, lot_size_sqft + the derived lot_size_acres, and portal_url_hyperlink). Per-target errors are captured per-row — one bad target will not fail the whole call. Calls are concurrent. The raw description is omitted by default; pass include_description: true to keep the marketing prose. listing_agent omits the agent's telephone/email unless include_agent_contact: true. The cross-row summary table duplicates per-property fields (~30% of response weight); it is OPT-IN via include_summary: true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewNoResponse shape: "compact" (default) drops fields the response already carries elsewhere; "full" returns every field this server understands. compact strips image/avatar URLs from the response; "full" returns Homes.com's payload untouched. No field projection: this server has no verified record of which Homes.com fields matter, and inventing one would risk dropping a field a caller needs.
targetsYesArray of 2–8 properties to compare
include_summaryNoWhen true, also emit a cross-row `summary` table aligned by field. Default false — the per-row records already carry every summary field, so the table is redundant context weight unless explicitly requested (#18).
include_descriptionNoWhen true, include the raw listing `description` marketing prose on each per-property record. Default false.
include_agent_contactNoWhen true, include the listing agent's `telephone` and `email` on `listing_agent`. Default false — name, job title, profile url and brokerage are returned without the contact details.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.5
    • addedInput schema / properties / include_agent_contact
      Added value: +{
+  "default": false,
+  "description": "When true, include the listing agent's `telephone` and `email` on `listing_agent`. Default false — name, job title, profile url and brokerage are returned without the contact details.",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv2.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. Changed1 schema field changedv1.4.1
    • addedInput schema / properties / view
      Added value: +{
+  "description": "Response shape: \"compact\" (default) drops fields the response already carries elsewhere; \"full\" returns every field this server understands. compact strips image/avatar URLs from the response; \"full\" returns Homes.com's payload untouched. No field projection: this server has no verified record of which Homes.com fields matter, and inventing one would risk dropping a field a caller needs.",
+  "enum": [
+    "compact",
+    "full"
+  ],
+  "type": "string"
+}
  4. First observedv1.1.1

TDQS

A4.7/5.0
Behavior5/5

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

Annotations (readOnlyHint, openWorldHint, idempotentHint) cover the safety profile, and the description adds substantial behavior beyond that: per-target error isolation ('one bad target will not fail the whole call'), concurrent execution, default omission of description/agent contact, and the ~30% response-weight rationale for the opt-in summary. This is exactly the kind of non-obvious runtime 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.

Conciseness5/5

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

Dense but every sentence earns its place: purpose first, then input requirement, return fields, error/concurrency semantics, then the three opt-in behaviors in a logical flow. The field list and opt-in explanations would normally be redundant with an output schema, but since none exists, they carry necessary information rather than padding.

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 and no nested objects, the description carries the full burden of explaining the return shape — and it delivers: the specific per-property fields, per-row error behavior, concurrency, and all three opt-in toggles are disclosed. The `view` parameter's response-shape semantics live in the schema (100% coverage), so nothing an agent needs to call 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 lifts it by adding cross-tool meaning for `url` (sourced from homes_search_properties) and behavioral rationale for the opt-in flags (what the 'description' prose is, which agent fields are withheld, why summary is redundant). It doesn't reach 5 because the schema already documents defaults and effects precisely, leaving the description to add context rather than essential meaning.

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?

Opens with a specific verb+resource: 'Fetch 2 or more homes.com properties and align their facts side-by-side.' The side-by-side comparison scope plus the 2+ count requirement distinguishes it from homes_get_property (single property) and homes_bulk_get (bulk fetch without alignment), so the purpose is unambiguous.

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?

Clear context: the tool is for comparing 2–8 properties, and the input guidance ('full homes.com property URL, e.g. from a homes_search_properties result's url field') actively routes agents to the correct sibling as the data source. However, there is no explicit when-not-to-use or named alternative for single-property lookups (homes_get_property) or bulk fetch (homes_bulk_get), so it stops short of a 5.

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