Homesage.ai MCP

Address Autocomplete

auto_complete_address

Read-only

What it returns

Up to 5 address suggestions matching a partial address string. Powered by a national address graph and curated to US street-level results only — city names, state codes, and ZIP codes alone return no matches.

When to use it

Power a typeahead input on a "lookup property" form.
Resolve user-typed input to a canonical address string before calling info / current-estimate.
Disambiguate between similar-named streets in the same city.

Pricing

Free — 0 credits. Safe to fire on every keystroke (debounce in the client recommended for cost-of-network, not credits).

Errors

Status	Meaning
400	`input` parameter missing or shorter than 2 characters.
401	Authentication failed.
503	Upstream address service unavailable. Retry with backoff.

FAQ

Does this work for commercial addresses?

No. Only US residential street addresses are returned. The endpoint upstream filters to area_type == "address" records only.

Can I autocomplete by ZIP code?

No — ZIP-only input returns an empty data array. Provide a street fragment with at least one number or street word.

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": {
      "input": "<input>"
    },
    "name": "auto_complete_address"
  }
}

Input Schema

Name	Required	Description	Default
`input`	Yes	Partial address. Minimum 2 characters. Example: `4411 E Hidden`.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so safety is covered. The description still adds real value beyond them: zero-credit pricing, per-keystroke safety, an error table with 400/401/503 semantics and retry-with-backoff guidance, and the upstream `area_type == "address"` filter. That said, it omits any mention of latency or rate limiting, so it is strong-but-not-rich rather than fully comprehensive.

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?

Well front-loaded — return shape first, then usage, pricing, errors, FAQ — and scannable with headers. Some content is paid for twice: the 2-character minimum appears in the schema, the error table, and the parameter prose, and the FAQ repeats the city/ZIP no-match rule already stated in the opening section.

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 one-parameter, free, read-only lookup, an agent has everything needed: what comes back, when to call it, what it costs, and how failures manifest. An output schema exists, so the brief return summary is a bonus rather than a gap-filler.

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% and the single parameter already documents the 2-character minimum with an example. The description still adds meaning: the input must contain a street fragment with at least one number or street word, and that violating the length floor produces a 400. It restates the 2-character minimum, which is redundant, but the street-fragment constraint is genuinely new.

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 and resource plus cardinality: "Up to 5 address suggestions matching a partial address string." It also carves out scope explicitly (US street-level only; city/state/ZIP alone return nothing), which separates it from the sibling `area_autocomplete` without needing to name it.

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?

Provides three concrete when-to-use scenarios (typeahead on a lookup form, canonicalizing input before `info` / `current-estimate`, disambiguating same-named streets) plus explicit when-not cases in the FAQ (no commercial addresses, no ZIP-only input). Alternative routing is stated, not inferred.

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

All Homesage.ai MCP 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?