Add a new domain to the organization. Response includes the reporting_email and dmarc_record values to publish in DNS. May return 402 if the plan domain limit has been reached.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Domain name to monitor (e.g. "example.com"). Stored lowercased. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the response includes reporting_email and dmarc_record values for DNS publication, and mentions a 402 error for plan domain limits. With no annotations, it carries some burden but does not cover other important behaviors like verification requirements, idempotency, or reversibility, so it is not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the main action, and includes essential behavioral notes (response values and error condition) without any irrelevant detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter creation tool, the description adequately covers the action, key response fields, and a common error. It could mention post-creation verification or duplicate domain behavior, but the current description is sufficient for basic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage; the 'name' parameter is well-described with examples and lowercasing behavior. The tool description does not add any additional parameter semantics, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Add a new domain to the organization' with a specific verb, resource, and scope. It also mentions the response includes reporting_email and dmarc_record values, which further clarifies the tool's purpose. This distinguishes it from sibling tools like delete_domain, get_domain, and list_domains.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies use for creating a new domain, providing clear context. However, it does not explicitly mention alternatives or exclusions, such as using verify_domain for post-creation verification. It gives no when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes (domain management, report retrieval, forensic reports, alerts, webhooks). The only potential confusion is between get_forensic_reports_summary and get_forensic_reports_statistics, which both aggregate forensic data but differ in scope and grouping.
Tool names consistently follow a verb_noun pattern (list_domains, create_webhook, delete_domain) with snake_case throughout. Minor deviations include singular/plural mix (get_forensic_report vs get_forensic_reports_statistics) and synonymous verbs (check_dmarc vs verify_domain), but overall the pattern is predictable.
With 21 tools, the set is on the heavier side for a DMARC monitoring server. While the multiple sub-domains (domains, reports, forensics, alerts, webhooks) justify many tools, some could potentially be consolidated (e.g., summary vs statistics variants), making the count feel slightly bloated.
The tool set covers the full lifecycle of each resource: domains have create/list/get/delete/verify, webhooks have full CRUD plus test, reports have list/get/export/statistics, forensic reports have list/get/summary/statistics, and alerts have list/dismiss. No obvious gaps or dead ends for DMARC monitoring workflows.
