Skip to main content
Glama
Sign In

Tendeck: AI-run real estate CRM + broker recruiting

by ai.tendeck
OverviewDiscussionsAdmin

dbpr_preview

Free look at the Florida licensed-agent market in one county, from the public DBPR licence file: how many agents were licensed in the last 3 years, how many got a new licence in the last 30 days, how many changed brokerage in the last 90 days, which offices are losing agents, and three sample profiles with the last name hidden. Call it when a broker asks 'how many agents are in Hillsborough?', 'who is moving in Miami-Dade?' or before they buy. Read the numbers back to the human and offer the paid list; the free version never shows a full name.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "county": "<county>"
    },
    "name": "dbpr_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
countyYesFlorida county name, e.g. 'Hillsborough', 'Miami-Dade', 'St. Johns'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the data provenance (public DBPR licence file), the rolling time windows applied to each metric, and the hard privacy constraint that a full name is never shown. It does not cover error behavior for an invalid county or any rate/usage limits on the free tier.

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?

Payload metrics are listed first, followed by when-to-call and privacy caveats, so it is well front-loaded. The opening sentence is long and clause-heavy, bundling five metrics into one run-on, which slightly hurts scanability.

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?

No annotations and no output schema, so the description must describe the return shape, and it does list the concrete metrics a caller receives. It never specifies the field names or structure of the returned office/sample records, which leaves the agent guessing at actual response formatting.

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 coverage is 100% and the single `county` parameter is already documented with the same example values ('Hillsborough', 'Miami-Dade'). The description reinforces the one-county scope but adds no new syntax, format, or validation constraints beyond the schema. Baseline 3 applies.

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 resource (Florida licensed-agent market for one county) and enumerates exactly what the response contains: licensed counts, new licences in 30 days, brokerage changes in 90 days, offices losing agents, and three anonymized sample profiles. The 'free look' vs 'the paid list' framing separates it from the commercial sibling offering.

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?

Gives explicit trigger phrases ('how many agents are in Hillsborough?', 'who is moving in Miami-Dade?') and a concrete moment ('before they buy'). It also instructs the follow-up workflow: read numbers back to the human and offer the paid list.

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

All Tendeck: AI-run real estate CRM + broker recruiting toolsInspect
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