Added value: +{
+  "default": "full",
+  "description": "'full' (default) returns every hit's full record. 'summary' is the cheap scan mode and the preferred first step: per hit only id, pillar, kind, title/subject, a one-line summary (~160 chars), score, matched_keyword (with explain=true) and provenance. Then call memory_get(ids=[...]) for the few records you will use. Summary mode ignores verbose.",
+  "enum": [
+    "full",
+    "summary"
+  ],
+  "type": "string"
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "ISO-8601 timestamp: answer from what was current at that instant (transaction time). created_at <= as_of and not retired before it; soft-deleted rows are never returned. Semantic and episodic memory only (no working buffer, graph expansion, playbooks, skills, strategy or work), read with the same scope and share rules as live recall; relative dates in the query are relative to as_of. Omit for live current truth. A future or unparseable value is a 422 invalid_body on as_of. When set, wins over include_superseded."
+}

Previous value: -"When true, include per-record retrieval attribution in metadata.ranking (base RRF, every factor, relevance floor verdict, diversity penalty; its score equals the hit's score), plus read-only feedback_score when votes exist"New value: +"When true, include per-record retrieval attribution in metadata.ranking (base RRF, every factor including bounded feedback trust from memory_feedback votes, relevance floor verdict, diversity penalty; its score equals the hit's score), plus read-only feedback_score when votes exist"

Previous value: -"When true, include per-record retrieval attribution in metadata, plus read-only feedback_score when votes exist"New value: +"When true, include per-record retrieval attribution in metadata.ranking (base RRF, every factor, relevance floor verdict, diversity penalty; its score equals the hit's score), plus read-only feedback_score when votes exist"

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Org-allowlisted container. When set, semantic/episodic hits outside this slug are excluded (not merely demoted). Omit to keep shared-org recall. repo=/github= still boost. Unknown slugs fail. Example: github:acme/app or project:alpha."
+}

Previous value: -"When true, include per-record retrieval attribution in metadata"New value: +"When true, include per-record retrieval attribution in metadata, plus read-only feedback_score when votes exist"

Added value: +{
+  "anyOf": [
+    {
+      "exclusiveMinimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional wall-clock budget for this call. Finished pillars are returned with errors_by_pillar timeout codes and degraded=true instead of letting the MCP client kill the whole call. Omit to use the server TEAMSHARED_RECALL_DEADLINE_SECONDS default (unset = no cutoff)."
+}

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional AND filter. Keys (all optional): kind (fact|preference|event|note|outreach|skill|procedure), pillar (semantic|episodic|procedural|skill|strategic|work), subject (exact, case-insensitive), tags (list; record must include every tag), since / until (ISO datetimes). Example: {\"kind\": \"fact\", \"subject\": \"HolderBrief\", \"tags\": [\"decision\"]}. Nested AND/OR/NOT is not supported — omit a key instead. Empty result retries once without the filter (filter_relaxed=true on the result). Not for named playbook/skill/entity — use get-by-name tools."
+}

Added value: +{
+  "default": false,
+  "description": "When true, also return superseded/merged history. Default is current truth only.",
+  "type": "boolean"
+}