Skip to main content
Glama
Sign In

WhiteMagic — governed local memory for agent continuity

by io.github.lbailey94
OverviewDiscussionsAdmin

WhiteMagic Meta-Tool

wm

Hosted router for available hosted tools. Use tools/list to discover supported routes.

Input Schema

NameRequiredDescriptionDefault
argsNoParameters for the routed tool
routeNoExplicit hosted tool route. Choose a supported tool from tools/list.
actionNoLegacy hosted action selector. Choose a supported tool from tools/list.
thoughtNoNatural language query or command auto-routed via NLU

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / action
      Added value: +{
+  "description": "Legacy hosted action selector. Choose a supported tool from tools/list.",
+  "type": "string"
+}
    • changedInput schema / properties / args / description
      Previous value: -"Arguments to pass through to the target tool."New value: +"Parameters for the routed tool"
    • changedInput schema / properties / thought / description
      Previous value: -"Natural language input describing what to do. Auto-routes to the best-matching tool via TF-IDF NLU classification."New value: +"Natural language query or command auto-routed via NLU"
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "description": "The dispatched tool's result envelope plus `_wm_route` dispatch metadata; fields vary by route.",
-  "properties": {
-    "_wm_route": {
-      "description": "Dispatch metadata: resolved tool, routing confidence, matched input.",
-      "properties": {
-        "confidence": {
-          "description": "Routing confidence (1.0 for explicit routes)",
-          "type": "number"
-        },
-        "input": {
-          "description": "Routing input that produced the match",
-          "type": "string"
-        },
-        "tool": {
-          "description": "Resolved route name",
-          "type": "string"
-        }
-      },
-      "type": "object"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedInput schema / properties / route / description
      Previous value: -"Explicit tool name for direct dispatch (e.g. 'memory.create', 'tools.list')."New value: +"Explicit hosted tool route. Choose a supported tool from tools/list."
  3. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  4. Changed2 schema fields changed
    • changedOutput schema / description
      Previous value: -"The dispatched tool's result envelope; fields vary by route."New value: +"The dispatched tool's result envelope plus `_wm_route` dispatch metadata; fields vary by route."
    • addedOutput schema / properties
      Added value: +{
+  "_wm_route": {
+    "description": "Dispatch metadata: resolved tool, routing confidence, matched input.",
+    "properties": {
+      "confidence": {
+        "description": "Routing confidence (1.0 for explicit routes)",
+        "type": "number"
+      },
+      "input": {
+        "description": "Routing input that produced the match",
+        "type": "string"
+      },
+      "tool": {
+        "description": "Resolved route name",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  }
+}
  5. First observed

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive, and closed-world behavior. The description adds the discovery prerequisite via tools/list, but does not explain that side effects and idempotency depend on the routed tool, or how lookup failures and routing errors behave.

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 with the purpose front-loaded. Both sentences earn their place: one identifies the router, the other states the discovery prerequisite.

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

Completeness3/5

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

The rich schema covers the four routing parameters, and annotations cover the safety profile, so the description is not required to carry everything. Still, for a meta-tool with nested args and multiple routing modes, the description is thin about the overall routing model.

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%, and the schema itself explains route, action, thought, and args. The description adds no parameter-level meaning beyond referring to routes, so the baseline 3 is appropriate when the schema does the heavy lifting.

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

Purpose3/5

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

The description calls itself a hosted router for hosted tools, which identifies a broad function, but it never defines what 'hosted tools' are or what routing actually does. It also does not distinguish this meta-tool from direct sibling tools such as memory.* or sutra.route.

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

Usage Guidelines2/5

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

The only usage guidance is to use tools/list to discover supported routes. It gives no guidance on when to choose this meta-tool over direct sibling tools, and no guidance on when to use route, action, or thought.

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