Skip to main content
Glama
agentisend

agentisend

Create sending domain

create_domain

Register a sending domain and get the exact DNS records to publish, plus TLS mode and tracking options. Use it to set up a domain before verifying it with verify_domain.

Instructions

Purpose: register a domain to send from, and get the exact DNS records to publish. NOT for: publishing those records — only whoever runs the DNS can do that — or checking them afterwards (verify_domain). Returns: the same domain view GET /domains/:id returns — every record with host, zone-relative name, value_strings, TTL, priority, required and observed, plus tls_mode (opportunistic by default, or enforced). The domain name is the name argument. Region is optional: us is the default, eu the other value. It is recorded on the domain; today all mail is sent from our US nodes, and eu domains move to EU sending automatically when it ships. A new domain reads pending while DNS spreads, which takes minutes to a day or two. Opportunistic — try TLS, fall back to plain when the receiver has none (the default). Enforced — refuse to deliver to a receiver that cannot do TLS; mail to such receivers bounces.

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": {
      "name": "<name>"
    },
    "name": "create_domain"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesDomain name, e.g. "acme.com".
regionNous or eu. Default us. Recorded on the domain; today all mail is sent from our US nodes, and eu domains move to EU sending automatically when it ships. Legacy names us-east-1, sa-east-1 and ap-northeast-1 map to us; eu-west-1 maps to eu.
tls_modeNoOpportunistic — try TLS, fall back to plain when the receiver has none (the default). Enforced — refuse to deliver to a receiver that cannot do TLS; mail to such receivers bounces.
trackingNoInclude the tracking records. Default true. false omits them. Tracking is never required to verify.
open_trackingNoRecord opens. Default false. Same field as POST /domains.
click_trackingNoRewrite links and record clicks. Default false. Same field as POST /domains.
idempotency_keyNoYour own key for this action. Retrying with the same key returns the first result instead of doing it twice — send one whenever a retry could double the effect.
tracking_subdomainNoRelative host for click and open links. Default links, which becomes links.yourdomain.com.
return_path_subdomainNoLabel for the return-path host, up to 63 characters, starting with a letter. send is the default. Pick another label, such as bounce, when send already has an MX pointing elsewhere.

Output Schema

NameRequiredDescriptionDefault
idNoIdentifier.
nameNo
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
regionNo
statusNopending, verified, failed or temporary_failure.
recordsNoEach DNS record with its status.
tls_modeNoopportunistic or enforced.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false. The description adds real context beyond that: the exact return shape (same as GET /domains/:id with host, zone-relative name, value_strings, TTL, priority, required, observed, tls_mode), that a new domain reads 'pending' while DNS spreads (minutes to a day or two), and the operational consequences of tls_mode='enforced' (mail to non-TLS receivers bounces).

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?

Front-loaded with labelled Purpose / NOT for / Returns blocks before the parameter prose, which is the right structure for a complex tool. It is dense and repeats the tls_mode definition already present in the schema, but each sentence largely earns its place given nine parameters and async semantics.

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 mutation tool with nine parameters, an output schema, and non-trivial propagation/TLS behavior, the description covers the essentials: what it creates, what comes back, the pending lifecycle, region recording, and the TLS delivery consequence. Nothing an agent needs in order to call it correctly appears missing.

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 description coverage is 100%, so the baseline is 3. The description does add framing beyond the schema by tying arguments to intent ('The domain name is the name argument', 'Region is optional: us is the default, eu the other value') and reiterating the tls_mode trade-off — useful, though largely duplicative of the enum descriptions.

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 with scope: 'register a domain to send from, and get the exact DNS records to publish.' It also draws the boundary against a named sibling ('NOT for ... checking them afterwards (verify_domain)'), so an agent can distinguish it from the read path without opening a schema.

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?

Gives explicit when-not guidance ('NOT for: publishing those records — only whoever runs the DNS can do that') and names verify_domain as the post-hoc check. However, it never addresses the closely related siblings setup_domain and wait_for_domain, leaving the agent to guess which of the three to pick for the register-then-verify workflow.

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