Groundmail

Verify domain

verify_domain

Idempotent

Verify DNS for a sending domain after records are applied.

Input Schema

Name	Required	Description	Default
`domain`	Yes	Domain name or id to check (example.com)

Output Schema

Name	Required	Description
`checks`	No	Result of each DNS check
`domain`	Yes	The domain
`records`	No	DNS records to publish for the domain
`verified`	Yes	True when the domain passed verification
`inbound_error`	No	Inbound setup error, if any
`signing_ready`	No	True when outgoing mail can be signed for this domain
`inbound_pending`	No	True while inbound setup is still in progress
`inbound_configured`	No	True when inbound receiving is set up

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedOutput schema / properties / domain / properties / blocklists

Added value: +{
+  "description": "Daily check of the domain and its main domain on Spamhaus DBL, SURBL and URIBL. A listing never pauses sending",
+  "properties": {
+    "checked_at": {
+      "description": "When the last daily blocklist check ran (ISO 8601)",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "listings": {
+      "description": "Current listings, main domain first",
+      "items": {
+        "properties": {
+          "info_url": {
+            "description": "Where to look the name up and request removal",
+            "type": "string"
+          },
+          "list": {
+            "description": "List name: Spamhaus DBL, SURBL or URIBL",
+            "type": "string"
+          },
+          "list_id": {
+            "description": "List id: spamhaus-dbl, surbl or uribl",
+            "type": "string"
+          },
+          "listed_since": {
+            "description": "When the daily check first found it listed (ISO 8601)",
+            "type": "string"
+          },
+          "name": {
+            "description": "The listed name: the domain itself or its main domain",
+            "type": "string"
+          },
+          "reason": {
+            "description": "What the list says it is listed for, for example spam domain",
+            "type": "string"
+          }
+        },
+        "required": [
+          "list",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "main_domain": {
+      "description": "The main (registrable) domain",
+      "type": "string"
+    },
+    "names": {
+      "description": "Names checked: the domain and its main domain, or one name for a main domain",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "removed": {
+      "description": "Recent removals, newest first",
+      "items": {
+        "properties": {
+          "info_url": {
+            "description": "Where to look the name up and request removal",
+            "type": "string"
+          },
+          "list": {
+            "description": "List name: Spamhaus DBL, SURBL or URIBL",
+            "type": "string"
+          },
+          "list_id": {
+            "description": "List id: spamhaus-dbl, surbl or uribl",
+            "type": "string"
+          },
+          "listed_since": {
+            "description": "When the daily check first found it listed (ISO 8601)",
+            "type": "string"
+          },
+          "name": {
+            "description": "The listed name: the domain itself or its main domain",
+            "type": "string"
+          },
+          "reason": {
+            "description": "What the list says it is listed for, for example spam domain",
+            "type": "string"
+          },
+          "removed_at": {
+            "description": "When it came off the list (ISO 8601)",
+            "type": "string"
+          }
+        },
+        "required": [
+          "list",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "Blocklist status: clear, listed, or unknown (not checked yet, not verified, or no list answered)",
+      "type": "string"
+    },
+    "unanswered_lists": {
+      "description": "Lists that did not answer the last check",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedOct 29, 2026

changedOutput schema / properties / checks / properties / spf / description

Previous value: -"SPF record found"New value: +"SPF in place. Always true for a main domain (example.com), which needs no SPF change"

addedOutput schema / properties / records / items / properties / already_set

Added value: +{
+  "description": "True when the domain already publishes a record that does this job (its own DMARC record). The value is what is there now: nothing to add or change, never publish a second one",
+  "type": "boolean"
+}

Changed1 schema field changedOct 18, 2026

addedOutput schema / properties / domain / properties / tenant

Added value: +{
+  "description": "External id of the tenant that owns the domain. Absent for a domain the whole account can use",
+  "type": [
+    "string",
+    "null"
+  ]
+}

First observedOct 16, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare this is a non-read-only, idempotent, open-world operation, so the agent knows it is a safe, repeatable network action. The description adds the sequencing constraint but doesn't explain whether DNS propagation delay causes transient failures or whether the call blocks until verified.

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?

A single front-loaded sentence with zero waste that conveys the action and its precondition in one read.

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 an output schema handling return values and annotations covering safety/idempotency, the description is nearly sufficient for a simple one-parameter tool. It could note behavior around propagation delays or retries, but no critical information is missing.

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?

Only one parameter with 100% schema description coverage, so baseline is 3. The description implies the domain must already have records applied but adds no interpretation of accepted domain name vs. id formats beyond the schema example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (verify) and resource (DNS for a sending domain) with a clear precondition (after records are applied). An agent can distinguish it from apply_domain_dns and create_domain, though it doesn't name those siblings explicitly.

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?

'After records are applied' gives helpful sequencing context, implying this follows apply_domain_dns. However, it never states when not to use it, what to do if verification fails (retry, poll), or names the alternative tools directly.

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

All Groundmail tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.