Skip to main content
Glama
chrischall

compass-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Compare Compass properties side-by-side

compass_compare_properties
Read-onlyIdempotent

Fetch 2 or more Compass properties and align their facts side-by-side. Each target may supply url (a full Compass homedetails URL or path) or listing_id_sha alone — sha-only targets fetch /listing//view, which redirects to the…

Instructions

Fetch 2 or more Compass properties and align their facts side-by-side. Each target may supply url (a full Compass homedetails URL or path) or listing_id_sha alone — sha-only targets fetch /listing//view, which redirects to the homedetails page. Returns the full per-property record per row (with extracted_features populated). Per-target errors are captured per-row — one bad target will not fail the whole call; a failed row carries status = error_kind (timeout / bridge_down / protocol / other), retryable and error, and the envelope reports count / ok / errored. Calls are concurrent, and the whole call is bounded by an overall deadline: any row still unsettled when it is reached comes back as { status: "pending", retryable: true, error } with a top-level pending count — re-run just those targets. The raw description is omitted from each row by default — pass include_description: true to keep it. The redundant summary table is also opt-in via include_summary: true — by default only results[] is returned, which already carries every fact.

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 Compass's payload untouched. No field projection: this server has no verified record of which Compass fields matter, and inventing one would risk dropping a field a caller needs.
targetsYesArray of 2–25 properties to compare. (Cap raised from 8 to 25 in #53; for unbounded structured fetch without the summary table, use `compass_bulk_get`.)
include_summaryNoInclude the pivoted `summary` table (one row per compared field, one column per listing). Defaults to `false` — `results[].property.*` already carries every fact and the summary was roughly 30% of response weight. Useful only for human-readable rendering.
include_descriptionNoInclude the raw `description` (Compass marketing copy) on each row. Defaults to `false` — `extracted_features` is always populated.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.1.10
    • changedInput schema / properties / targets / items / properties / listing_id_sha / description
      Previous value: -"Compass listing identifier. Sufficient on its own — the tool resolves the address slug internally via site search before fetching the homedetails page."New value: +"Compass listing identifier (the SHA inside `<sha>_lid`). Sufficient on its own — the tool fetches /listing/<sha>/view, which 302-redirects to the slugged homedetails page (no extra lookup)."
    • 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 Compass's payload untouched. No field projection: this server has no verified record of which Compass fields matter, and inventing one would risk dropping a field a caller needs.",
+  "enum": [
+    "compact",
+    "full"
+  ],
+  "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 observedv0.12.1

TDQS

A4/5.0
Behavior5/5

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

Goes far beyond the readOnly/openWorld/idempotent annotations: per-row error capture that prevents one bad target from failing the whole call, specific error_kinds (timeout/bridge_down/protocol/other) with retryable and error fields, concurrency, an overall deadline with a pending status, envelope counts (count/ok/errored/pending), and default suppression of description and summary. This is exactly the kind of failure-mode and resource-bounding detail an agent needs before invoking.

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 core action, then proceeds through per-target input, failure semantics, and defaults in a logical order. It is dense and every sentence carries information, though the single long sentence covering error kinds and envelope keys requires close reading.

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 read-only comparison tool with no output schema, the description fully arms the agent: input forms, redirect path, per-row success/failure contract, retry strategy for pending rows, and the opt-in flags determining response shape. Nothing material is absent.

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 description coverage is already 100%, so the schema documents url, listing_id_sha, view, the toggles, and the min/max bounds. The description reinforces the default-off behavior of description/summary and the sha-only redirect path, but adds no syntax or constraints the schema lacks. Baseline 3 given full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The title and the opening sentence both state a specific verb and resource: fetch 2+ Compass properties and align their facts side-by-side. That distinguishes it from compass_get_property (single fetch) and from compass_bulk_get, which is mentioned later in the schema yet only as an aside. Purpose is clear, though it doesn't sharpen the boundary against compass_bulk_get within the description front-end.

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 description explains how to drive each target (url vs sha) and how to handle pending rows, but says nothing about when to pick this tool over compass_get_property or compass_bulk_get. The only comparison guidance is buried in the schema for targets, not the description. Usage is implied by behavior rather than stated.

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