NYC Property Facts

Deed / sales history (ACRIS)

get_sales_history

Read-onlyIdempotent

Deeds recorded with the NYC City Register (ACRIS) for a property: date, stated price (0 = non-market transfer), grantors, grantees, and whether the deed covers several lots. Requires one of "address", "bbl" or "bin".

Input Schema

Name	Required	Description
`bbl`	No	10-digit BBL (borough-block-lot), e.g. "3030090016". Send it as text.
`bin`	No	7-digit DOB building number (BIN), e.g. "3070696". Send it as text.
`zip`	No	Optional 5-digit ZIP, sent as text
`limit`	No	Maximum deeds returned
`address`	No	NYC street address, e.g. "98 Grattan St, Brooklyn". Units (Apt 3B), borough and ZIP are optional; a 10-digit BBL or 7-digit BIN also works.
`borough`	No	Optional: Manhattan, Bronx, Brooklyn, Queens or Staten Island

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 1, 2026

changedInput schema / properties / bbl / description

Previous value: -"10-digit BBL (instead of address)"New value: +"10-digit BBL (borough-block-lot), e.g. \"3030090016\". Send it as text."

addedInput schema / properties / bin

Added value: +{
+  "description": "7-digit DOB building number (BIN), e.g. \"3070696\". Send it as text.",
+  "type": "string"
+}

addedInput schema / properties / borough

Added value: +{
+  "description": "Optional: Manhattan, Bronx, Brooklyn, Queens or Staten Island",
+  "type": "string"
+}

addedInput schema / properties / limit / description
```
Added value: +"Maximum deeds returned"
```

addedInput schema / properties / zip

Added value: +{
+  "description": "Optional 5-digit ZIP, sent as text",
+  "type": "string"
+}

First observedNov 1, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/closed-world, so the safety profile is covered. The description adds genuine domain behavior the annotations cannot: the data source (ACRIS), the meaning of price = 0 (non-market transfer), and the multi-lot deed flag. It stops short of disclosing ordering, pagination, or what an empty result means.

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?

Two tight sentences: the first front-loads what is returned, the second front-loads the input constraint. No filler, no restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully compensates by listing returned fields, and it covers the key input constraint for a 6-parameter tool. Gaps remain around result ordering, the 25/200 limit behavior, and how deduplication across multiple lots works.

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; the description earns an extra point by stating the at-least-one-of address/bbl/bin constraint, which the schema's empty required array does not express. It does not add format or interaction detail for limit, zip, or borough beyond the schema.

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 (deeds recorded with NYC ACRIS for a property) and enumerates the returned fields (date, price, grantors, grantees, multi-lot flag), which clearly separates it from the sibling property-lookup tools. An agent can identify the resource and result shape from the first clause alone.

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 'Requires one of address, bbl or bin' sentence gives the agent an input-selection rule, but there is no explicit when-to-use guidance, no mention of when to prefer get_property or search_properties instead, and no exclusions. Usage is only implicitly conveyed.

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

All NYC Property Facts tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?