No user-submitted related servers found.
Scored across 27 tools
Most tools have clearly distinct purposes and the descriptions cross-reference related tools, so an agent can usually select correctly. However review vs review_signals and search/retrieve/recall are close enough that a model needs to read carefully to avoid selecting the wrong read/evaluate variant.
All tools share the shadowgraph_ prefix and snake_case style, which gives the surface a consistent feel. But the pattern mixes bare verbs (review, rebuild, search), noun phrases (context, journal, confidence_evidence), and verb_noun forms (record_decision, purge_preview), so it is not fully predictable.
27 tools is above the threshold for a heavy surface, and several clusters are over-fragmented: search/retrieve/recall/context/traverse, review/review_signals, and purge/purge_preview could be consolidated. While the domain is broad, the count feels excessive for an agent to navigate.
The core decision/memory lifecycle is well covered: record, recall, update, supersede, review, backup, restore, purge. The main gaps are the explicitly missing unlink operation for relationships and no direct apply tool for repair_plan, though agents can work around these via other tools.
