Scored across 16 tools
Most tools have distinct purposes, especially the paired registration and vocabulary tools. However, there is some boundary overlap among identity-oriented tools (alter_resolve_handle, alter_verify, alter_presence_read, alter_whoami) and among onboarding helpers (hello_agent, get_started, recommend_tool), though descriptions do enough to separate them.
All names are snake_case, but conventions are mixed: some use verb_noun (get_network_stats, describe_traits), some use an alter_ prefix (alter_resolve_handle, alter_whoami), and a few are noun-only (golden_thread_status, thread_census). The verbs also vary (get, list, describe, recommend, register, hello), making the set feel inconsistent even though each name is readable.
At 16 tools the set is slightly above the ideal 3-15 range, but the count is still justifiable for the breadth of identity infrastructure, onboarding, and reference data. The extra tools mostly pull their weight, so the count feels only modestly heavy rather than bloated.
The surface has significant gaps: tools like describe_traits and describe_competencies explicitly reference composing query_field and create_requirement operations, but those tools are not included, leaving obvious dead ends. There is also no way to update presence, manage keys, or perform the paid data operations that the server's own descriptions imply should exist.