Skip to main content
Glama

Property Records

by io.github.pipeworx-io

Property Lookup

property_lookup
Read-onlyIdempotent

Address-level US property records from county and city open-data portals — keyless public records, no API key. Answers "when did this house last sell", "how much did sell for", "who owns this property", "what is the assessed value of ", "property sale history", "county assessor data for an address". Returns the property sale history (dated transactions with price where the county publishes it), current assessed value, owner of record, parcel id (DC SSL / NYC BBL / Philadelphia OPA account / Cook County PIN / SF block-lot), land use or building class, year built, square footage, and bed/bath counts where available. SUPPORTED JURISDICTIONS ONLY — property records are maintained per county and there is no national keyless source. Currently covered: dc (Washington, District of Columbia); nyc (New York City (Manhattan, Bronx, Brooklyn, Queens, Staten Island)); philadelphia (Philadelphia, Pennsylvania); cook (Cook County, Illinois (Chicago and suburbs)); sf (San Francisco, California). An address in any other county returns covered:false with the inferred jurisdiction and the supported list, so you can tell the user plainly that this county is not in the dataset rather than guessing. Call property_coverage first if you want the field-by-field capability matrix. Examples: {"address":"1642 30th St NW, Washington DC"} → DC row house, SSL 1282 0198, owner, $1,354,300 assessed, sold 2012-08-09 for $1,085,000, 3 bed / 2.5 bath / 1,510 sqft built 1907. {"address":"232 East 6th Street, Manhattan"} → NYC BBL 1004610024 with the 2016-present sale list. {"address":"228 Spruce St, Philadelphia"} → full recorded deed chain with grantor/grantee. {"address":"3000 N Sheffield Ave, Chicago"} → Cook County PIN, sale, assessed value. {"address":"450 Sutter St, San Francisco"} → assessed value and characteristics (no price — SF does not publish it).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addressYesStreet address as free text. City / state / ZIP are optional but improve jurisdiction inference, e.g. "1600 Pennsylvania Ave NW", "232 East 6th Street, New York, NY 10003", "3000 N Sheffield Ave, Chicago IL". Punctuation, casing, and Ave/Avenue or St/Street spelling are all handled.
max_salesNoMaximum sale/transfer records to return, 1-50 (default 20, newest first).
jurisdictionNoOptional. Skip inference and query a specific portal. One of: dc | nyc | philadelphia | cook | sf.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "address": "1600 Pennsylvania Ave NW, Washington DC"
+  },
+  {
+    "address": "232 East 6th Street, Manhattan, NY 10003",
+    "max_sales": 10
+  }
+]
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only/idempotent, so the description adds valuable context: keyless access, jurisdiction scope, covered:false responses for unsupported counties, data variations (SF no price), and dependence on county publication. No contradiction with annotations.

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 description is long but front-loaded with the core purpose and well-structured with examples and jurisdiction list. Every sentence contributes useful information, though 'keyless public records, no API key' is slightly redundant.

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 compensates thoroughly: it states return fields, demonstrates via concrete examples, explains unsupported-jurisdiction behavior, and notes per-jurisdiction data limitations. This gives an agent full context for selecting and invoking the tool.

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%, but the description adds meaning by explaining address as free text with flexible formatting and optional city/state/ZIP improving inference, and it lists valid jurisdiction values in prose. This exceeds the baseline schema-only understanding.

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?

The description clearly states it retrieves address-level US property records from county/city open-data portals, lists specific questions it answers, and explicitly distinguishes itself from the property_coverage sibling by directing callers to that tool for a capability matrix.

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?

It names property_coverage as an alternative for capability-matrix queries and clearly explains supported jurisdictions plus the behavior for unsupported addresses (covered:false). It doesn't explicitly say 'use when not appropriate,' but the jurisdiction limitation and covered:false response make the usage context unmistakable.

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

All Property Records toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Multiple tools overlap heavily: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical variants of the same router, and there are six polymarket-related tools with overlapping arb/edge/fill-risk purposes. Property-specific tools are distinct but buried among many unrelated meta-tools.

Naming Consistency3/5

All names use snake_case, but the structural pattern is inconsistent: some are verb_noun (ask_pipeworx, validate_claim), others noun_verb (property_lookup), and many are noun_noun (entity_profile, polymarket_arbitrage). No clear systematic convention across the set.

Tool Count2/5

33 tools is far too many for a server labeled 'Property Records'—only two tools (property_lookup, property_coverage) actually serve that purpose. The rest belong to unrelated domains (general data lookup, prediction markets, memory, subscriptions), making the surface feel bloated and unfocused.

Completeness2/5

For a property-records server, the surface is incomplete: it only provides lookup plus a coverage matrix, with no other property-related operations (e.g., tax history, comparable sales) and no way to handle unsupported jurisdictions beyond a simple flag. The unrelated tools do not contribute to the stated domain, leaving the core purpose thinly covered.

Resources