Skip to main content
Glama
Sign In

WhiteMagic — governed local memory for agent continuity

by io.github.lbailey94
OverviewDiscussionsAdmin

Memory Revisions

memory.revisions
Read-onlyIdempotent

List the durable revision chain of a memory, or verify it by recomputing content hashes and chain links.

Input Schema

NameRequiredDescriptionDefault
idYesMemory UUID or record_id to inspect
actionNoAction: 'list' (default) or 'verify'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Action: list (default) | verify"New value: +"Action: 'list' (default) or 'verify'"
    • addedInput schema / properties / action / enum
      Added value: +[
+  "list",
+  "verify"
+]
    • removedInput schema / properties / galaxy
      Removed value: -{
-  "description": "Galaxy (default: codex)",
-  "type": "string"
-}
    • changedInput schema / properties / id / description
      Previous value: -"Memory UUID to inspect"New value: +"Memory UUID or record_id to inspect"
    • removedInput schema / properties / id / type
      Removed value: -"string"
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "description": "Revision chain for a memory (newest first).",
-  "properties": {
-    "action": {
-      "description": "Action performed (list, restore, ...)",
-      "type": "string"
-    },
-    "count": {
-      "description": "Number of revisions returned",
-      "type": "integer"
-    },
-    "galaxy": {
-      "description": "Galaxy containing the memory",
-      "type": "string"
-    },
-    "id": {
-      "description": "Memory UUID",
-      "type": "string"
-    },
-    "revisions": {
-      "description": "Revision records with content hashes and timestamps",
-      "items": {
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "status": {
-      "description": "Operation status",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed2 schema fields changed
    • changedOutput schema / description
      Previous value: -"Result envelope for this tool; fields vary by operation."New value: +"Revision chain for a memory (newest first)."
    • addedOutput schema / properties
      Added value: +{
+  "action": {
+    "description": "Action performed (list, restore, ...)",
+    "type": "string"
+  },
+  "count": {
+    "description": "Number of revisions returned",
+    "type": "integer"
+  },
+  "galaxy": {
+    "description": "Galaxy containing the memory",
+    "type": "string"
+  },
+  "id": {
+    "description": "Memory UUID",
+    "type": "string"
+  },
+  "revisions": {
+    "description": "Revision records with content hashes and timestamps",
+    "items": {
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "status": {
+    "description": "Operation status",
+    "type": "string"
+  }
+}
  4. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description adds genuinely new behavioral context by explaining that 'verify' is not a plain read but a recomputation of content hashes and chain links, which tells the agent the call does work and could be costlier. It stops short of noting that verification may surface mismatch results or fail on a broken chain.

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?

A single sentence, front-loaded with the primary action and resource, with the secondary verification mode immediately following. Nothing is redundant and no sentence needs trimming.

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

Completeness4/5

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

With only two parameters, full schema coverage, and no output schema, the definition covers what an agent needs to select and invoke it. It is slightly thin on what a listed revision entry contains and on what a failed verification looks like.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description pushes it higher by explaining what the 'verify' enum value actually does (hash recomputation plus chain-link checks), giving meaning beyond the schema's bare "'verify'" label, though it does not clarify the id format or expected scale of 'list'.

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

Purpose5/5

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

States a specific verb pair (list / verify) against a specific resource (the durable revision chain of a memory), which is clearly distinct from siblings like memory.read, memory.list, or memory.associations. An agent can tell what this returns without opening the schema.

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

Usage Guidelines4/5

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

The description distinguishes the two modes of use: 'list' to inspect the chain and 'verify' to check integrity, and the schema marks 'list' as the default. It gives clear context for choosing an action but names no alternative tools or when-not conditions.

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 toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources