Each tool maps to a distinct action and object: creating claims, adding evidence, tracking or updating assumptions, reviewing, retrieving context, and checking health. The boundaries between review and context retrieval, and between creating and updating assumptions, are clear from the descriptions.

All tools use the same cortex_ prefix and snake_case conventions, with mostly verb_noun names such as create_claim, add_evidence, and get_context. Minor deviations are cortex_health, a noun, and cortex_review, a bare verb.

Seven tools is well-scoped for a claim/evidence/assumption review server. Each tool has a clear role without obvious redundancy.

The surface covers the core workflow of creating claims, attaching evidence, tracking assumptions, reviewing, and retrieving context. Minor gaps exist around updating or deleting claims and evidence, but the append-only audit-style design may make some of these unnecessary.