Create an A/B test on a campaign with two or more variants. A sample percentage is sent first; the winner goes to the remainder once selected.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | What to test | |
| variants | Yes | Test variants (2–5) | |
| campaign_id | Yes | Campaign to test | |
| winner_metric | No | Metric used to pick the winner (default open_rate) | |
| sample_percentage | No | Percent of the audience used for the test (default 20) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnlyHint=false and destructiveHint=false, which are consistent with a creation tool. The description adds value by disclosing the two-phase behavior (sample sent first, winner later) and implicitly that the tool does not automatically select the winner. No contradiction with annotations.
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?
Two sentences with no wasted words. The first sentence states the purpose, the second describes the process. Information is front-loaded and easy to parse.
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?
No output schema is provided, and the description does not mention the return value (e.g., test ID). Prerequisites like campaign existence are not mentioned. The description explains the process but omits key context about what the tool actually returns.
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?
Schema description coverage is 100% with clear parameter descriptions. The description adds minimal value beyond the schema, only hinting at the process. Baseline 3 is appropriate as the schema already documents the parameters well.
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 the verb 'Create' and the resource 'A/B test on a campaign', and explains the two-phase process (sample then winner). It distinguishes from sibling tools like 'select_ab_test_winner' and 'list_ab_tests' by describing the creation action.
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 implies the tool is used to start an A/B test and mentions the process flow, but it does not explicitly state when to use this tool versus alternatives (e.g., using 'select_ab_test_winner' later). No exclusions or prerequisites are given.
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 are cleanly separated by resource and action, and the descriptions do a good job of cross-referencing related tools. However, there are several close clusters—get_analytics vs generate_report, get_deliverability_score vs run_deliverability_audit, check_dmarc vs verify_domain, and list_emails vs list_inbox_conversations vs get_email—that could cause an agent to pick the wrong one. The detailed descriptions reduce but do not eliminate this ambiguity.
Tool names follow a consistent snake_case verb_noun pattern throughout: create_, get_, list_, send_, toggle_, and so on. Even multi-word actions like select_ab_test_winner and categorize_inbox_emails stay uniform. The only slight deviation is the bare verb upgrade, but it is readable and does not break the overall pattern.
54 tools is far beyond the typical well-scoped MCP surface and lands heavily in the 'too many' range. While the domain is broad, many tools could be consolidated—multiple analytics/reporting tools, several deliverability checks, and separate email/inbox listing tools create redundancy. The sheer number increases selection overhead and makes the toolset harder for an agent to navigate reliably.
The core email marketing lifecycle is represented: domains, contacts, campaigns, templates, automations, sends, and analytics all have main operations. However, there are notable gaps—no update/delete for campaigns, templates, forms, or automations; no create/update/delete for forms; no sandbox enable/disable; and no way to install marketplace items. These are workable gaps but would cause failures for agents trying to perform full lifecycle management.