Skip to main content
Glama

Lob Verify Address

lob_verify_address
Read-onlyIdempotent

Verify a single US address for deliverability and return USPS-standardized/corrected components (ZIP+4, DPV codes, county, lat/lon). Pass structured components (primary_line, city, state, zip_code) OR a single freeform address string, not both. Example: lob_verify_address({ primary_line: "185 Berry St", secondary_line: "Ste 6100", city: "San Francisco", state: "CA", zip_code: "94107", _apiKey: "your-key" }) or lob_verify_address({ address: "185 Berry St Ste 6100 San Francisco CA 94107", _apiKey: "your-key" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "_apiKey": "your-lob-api-key",
      "address": "185 Berry St Ste 6100 San Francisco CA 94107"
    },
    "name": "lob_verify_address"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity name, e.g. "San Francisco".
stateNoTwo-letter state code, e.g. "CA".
_apiKeyYesYour Lob API key (sign up at https://dashboard.lob.com/).
addressNoFull single-line address, e.g. "185 Berry St San Francisco CA 94107". Use this OR the component fields, not both.
zip_codeNoZIP or ZIP+4, e.g. "94107".
primary_lineNoPrimary street address line, e.g. "185 Berry St".
secondary_lineNoSecondary line (apt/suite/unit), e.g. "Ste 6100". Optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, so the description doesn't need to repeat safety traits. It adds genuine value by naming the returned artifacts (ZIP+4, DPV codes, county, lat/lon) and the notion of address 'correction', which is important since no output schema exists. It doesn't cover what happens on an undeliverable address, but the gap is minor.

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?

Purpose and return values are front-loaded in the first clause, with the input-mode rule right after. The two full JSON-style examples take considerable space and partly restate the schema, but they are immediately useful for correct invocation.

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?

For a 7-parameter, no-output-schema tool with annotations already covering safety, the description is essentially complete: it says what comes back, how to supply the address, and how not to. Only the failure/undeliverable path is unstated, which keeps it from a 5.

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 the baseline is 3; the description earns above that by reinforcing the either/or constraint between `address` and the component fields and by showing complete worked calls including `_apiKey`. It does not, however, add semantics the schema lacks for fields like secondary_line or DPV interpretation.

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 leads with a specific verb and resource ('Verify a single US address') plus the concrete output set (ZIP+4, DPV, county, lat/lon). The word 'single' implicitly separates it from the bulk sibling lob_verify_bulk, and 'US' bounds the scope so an agent won't route non-US addresses here.

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 clearly states the two mutually exclusive input modes ('Pass structured components ... OR a single freeform `address` string, not both'), which is the main invocation decision an agent faces. What's missing is explicit when-to-use-this-vs-lob_autocomplete or lob_verify_bulk guidance, so it stops short of full alternative routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.