Scored across 57 tools
Most tools have clearly differentiated purposes, especially around document CRUD, snapshots, search modes, and export. However, the cluster of analysis and feedback tools—analyze_document, analyze_writing_style, check_consistency, check_plot_consistency, and suggest_improvements—has meaningful overlap and requires careful description-reading to select correctly.
The naming convention is overwhelmingly verb_noun snake_case with consistent prefixes like get_, list_, create_, read_, write_, and set_. A few bare-verb or noun-style exceptions such as search, remember, recall, and character_network deviate slightly, preventing a perfect score.
At 57 tools, this server is in the extreme mismatch range and presents a very heavy namespace for agents to navigate. The skills-based progressive disclosure mitigates discovery cost, but it does not reduce the total surface, and many analysis and generation tools could likely be consolidated.
The tool surface covers the full Scrivener workflow: project discovery and session lifecycle, document CRUD and trash recovery, snapshots, metadata, multiple search modes, AI analysis and generation, goals, memory, relationship graphs, compile/export, and background jobs. There are no obvious dead ends for the stated domain.