WhiteMagic — governed local memory for agent continuity

Hybrid recall (compatibility alias)

memory.hybrid_recall

Read-onlyIdempotent

Compatibility alias of memory.search — same implementation, same arguments, same results. Kept for clients pinned to this name; prefer memory.search.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum results (default 10; must be >= 1)
`query`	Yes	Full-text query
`since`	No	Inclusive lower time bound: RFC3339 ('2026-02-01T00:00:00Z') or epoch seconds
`until`	No	Inclusive upper time bound: RFC3339 or epoch seconds
`galaxy`	No	Galaxy filter (optional; default: search all memory galaxies, results labeled; "all" is accepted as an alias for the unfiltered default)
`min_score`	No	Absolute BM25 score floor
`min_trust`	No	Minimum source_trust (0-1): drop results below this trust floor
`time_basis`	No	Time basis for since/until: 'recorded' (created_at, default) or 'event' (event_time, falling back to created_at when unset)
`include_cold`	No	Opt-in unranked cold recovery (no thaw). Trust/importance floors apply; BM25 floors do not apply to unscored recovery. Search content is scrubbed navigation capped at 8192 characters; read by id/galaxy for the exact original.
`min_importance`	No	Minimum memory importance (0-1)
`cold_scan_limit`	No	Maximum cold records to scan when include_cold is set (default 2048)
`min_score_ratio`	No	Relative floor: reject hits below this fraction of the top score

Output Schema

TableJSON Schema

Name	Required	Description
`hint`	No	Optional recovery hint when results are thin (null when there is none)
`count`	No	Number of results returned
`galaxy`	No	Galaxy scope the query ran against
`status`	No	Operation status
`results`	No	Ranked memories with per-result source labels
`recall_mode`	No	Retrieval path used (hybrid, episodic, fts, importance, none)
`evidence_bundle`	No	Per-result provenance (coverage, history, integrity, retrieval, source_time, visibility) plus conflicts.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 1, 2026

addedInput schema / properties / since

Added value: +{
+  "description": "Inclusive lower time bound: RFC3339 ('2026-02-01T00:00:00Z') or epoch seconds",
+  "type": "string"
+}

addedInput schema / properties / time_basis

Added value: +{
+  "description": "Time basis for since/until: 'recorded' (created_at, default) or 'event' (event_time, falling back to created_at when unset)",
+  "type": "string"
+}

addedInput schema / properties / until

Added value: +{
+  "description": "Inclusive upper time bound: RFC3339 or epoch seconds",
+  "type": "string"
+}

Changed3 schema fields changedSep 28, 2026

changedOutput schema / description

Previous value: -"Fused recall results with an evidence bundle and recall-mode disclosure."New value: +"Recall results (memory.search implementation) with an evidence bundle and recall-mode disclosure."

changedOutput schema / properties / hint / description

Previous value: -"Optional recovery hint when results are thin"New value: +"Optional recovery hint when results are thin (null when there is none)"

changedOutput schema / properties / hint / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

Changed2 schema fields changedSep 24, 2026

changedOutput schema / description

Previous value: -"Result envelope for this tool; fields vary by operation."New value: +"Fused recall results with an evidence bundle and recall-mode disclosure."

addedOutput schema / properties

Added value: +{
+  "count": {
+    "description": "Number of results returned",
+    "type": "integer"
+  },
+  "evidence_bundle": {
+    "description": "Per-result provenance (coverage, history, integrity, retrieval, source_time, visibility) plus conflicts.",
+    "type": "object"
+  },
+  "galaxy": {
+    "description": "Galaxy scope the query ran against",
+    "type": "string"
+  },
+  "hint": {
+    "description": "Optional recovery hint when results are thin",
+    "type": "string"
+  },
+  "recall_mode": {
+    "description": "Retrieval path used (hybrid, episodic, fts, importance, none)",
+    "type": "string"
+  },
+  "results": {
+    "description": "Ranked memories with per-result source labels",
+    "items": {
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "status": {
+    "description": "Operation status",
+    "type": "string"
+  }
+}

First observedSep 22, 2026

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description's only added behavioral claim is equivalence of implementation, arguments and results with memory.search — useful but thin; it says nothing about recall semantics, latency, or behavior on cold/unindexed data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, with the identity of the tool front-loaded and the routing recommendation immediately after. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an alias tool with an output schema, complete parameter documentation and rich annotations, the description supplies exactly the missing piece — that this is not a distinct capability and should not be chosen over memory.search unless the client is pinned to the name.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% across all 12 parameters, so the schema carries full parameter semantics (limits, time bounds, trust/importance floors, cold recovery). The description adds no parameter-level detail beyond declaring the arguments identical to memory.search; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states precisely what this tool is — a compatibility alias of memory.search with identical implementation, arguments and results — and names the canonical sibling, so an agent can route without opening either schema. It does not independently describe the underlying operation (memory search/recall), deferring that to memory.search, which keeps it just short of a self-contained 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit use condition ('kept for clients pinned to this name') and an explicit preference ('prefer memory.search'), which is exactly the when/when-not/alternative guidance the dimension asks for.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All WhiteMagic — governed local memory for agent continuity tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?