Loading ToolBench
Newsletter Growth MCP for creators. Growth loops, 6-email welcome sequence architecture, subject-line auditing, list-metric interpretation, monetization readiness (own product, per-click sponsorships, flat placements).
Newsletter Growth MCP has well-structured tool definitions with clear, domain-specific descriptions (avg 180 chars, within baseline 194). All 6 tools have input schemas with typed parameters and enums where appropriate. However, output schemas are entirely undocumented, no return type specifications visible in code. Parameter descriptions are present but inconsistent in depth. Tool names follow verb_noun convention (growth_loop_selector, welcome_sequence_builder). No error handling guidance, no recovery paths, and no security considerations documented. Composition is sound (each tool has one responsibility), but missing output documentation and error classification significantly limits LLM reasoning about downstream chaining.
Recommends which growth loop (lead magnet, social repurpose, cross-promo, referral, sponsorship swap) fits your current list size, platform reach, and content output. Returns the loop name, mechanism, when it wins, execution rules, and failure modes.
Interprets email list metrics (open rate, click rate, growth rate, unsubscribe rate, reply rate) against healthy benchmarks for creator lists. Returns diagnostic guidance on what each metric means and what to fix.
Evaluates whether your list is ready for monetization (own product, per-click sponsorships, flat placements) based on size, engagement, and niche. Returns readiness verdict and specific thresholds you need to hit.
Provides guidance on sponsorship deal terms, pricing models (per-click, flat placement, CPM), and negotiation frameworks for newsletter creators at different list sizes.
Audits a subject line against spam filters, mobile truncation, specificity, and engagement patterns. Returns a verdict (PASS/NEEDS WORK), character count, and specific issues with rules and details.
Generates a 6-email welcome sequence architecture with timing, job (purpose), and subject-line shape for each email. Explains why each email matters and the rules for execution.
No output schemas documented. Tools return structured data (verdict, metrics, guidance) but LLMs cannot see what fields to expect. Breaks downstream tool chaining and forces LLMs to guess field names.
No error handling or recovery guidance. Tools provide domain logic but no error classification (retryable vs user-fixable vs fatal). LLMs cannot self-correct on invalid input.
Parameter descriptions lack format/range constraints. E.g., 'list_size' (number) has no min/max bounds; LLMs could pass negative or absurdly large values. 'niche' (string) has no length or pattern guidance.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 48 | 2026-07-28+ | v2 |
Tool descriptions lack 'when to use' guidance. E.g., subject_line_auditor describes what it does but not when an LLM should call it vs. skipping it. Reduces tool selection clarity.
No idempotency guarantees documented. Tools like welcome_sequence_builder and sponsorship_deal_terms_guide are read-only (safe), but no explicit idempotent hints in schema. Agents cannot confidently retry on ambiguous failures.