Skip to main content
Glama
Sign In

WhiteMagic — governed local memory for agent continuity

by io.github.lbailey94
OverviewDiscussionsAdmin

Associative Graph Neighbours

memory.associations
Read-onlyIdempotent

Traverse associative graph neighbours of a memory over hub-penalized multi-hop spreading activation.

Input Schema

NameRequiredDescriptionDefault
idYesSource memory UUID or numeric record_id
hopsNoSpreading activation depth in hops (1 to 3, default: 1)
decayNoPer-hop spreading activation decay factor (default: 0.75)
limitNoMaximum neighbours to return (default: 10)
directionNoDirection: from | to | both (default: both)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / decay
      Added value: +{
+  "description": "Per-hop spreading activation decay factor (default: 0.75)",
+  "maximum": 1,
+  "minimum": 0.01,
+  "type": "number"
+}
    • addedInput schema / properties / hops
      Added value: +{
+  "description": "Spreading activation depth in hops (1 to 3, default: 1)",
+  "maximum": 3,
+  "minimum": 1,
+  "type": "integer"
+}
    • changedInput schema / properties / id / description
      Previous value: -"Memory UUID to inspect"New value: +"Source memory UUID or numeric record_id"
    • removedInput schema / properties / id / type
      Removed value: -"string"
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "Maximum neighbours to return (default: 10)",
+  "type": "integer"
+}
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "description": "Result envelope for this tool; fields vary by operation.",
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  3. Added

TDQS

B3.2/5.0
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 without description help. The description contributes only the concepts of hub penalization and multi-hop activation — no explanation of what a 'hub' is, how penalization affects ranking, or what the returned neighbours look like (no output schema exists to compensate).

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

Conciseness4/5

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

A single front-loaded sentence with no filler. It is efficient, though the density of undefined domain jargon ('hub-penalized spreading activation') reduces its usefulness per word rather than improving it.

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?

A 5-parameter traversal tool with no output schema leaves the description responsible for explaining what comes back — ranked neighbours, activation scores, edge metadata — and it says none of this. The safety behaviour is covered by annotations and the parameters by the schema, so it is minimally viable but clearly incomplete on return shape and result ordering.

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%, so id, hops, decay, limit and direction are all fully documented in the schema, setting the baseline at 3. The description's 'multi-hop' and 'hub-penalized' hints loosely map to hops and decay but add no operational detail beyond what the schema already gives.

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?

States a specific verb and resource — 'Traverse associative graph neighbours of a memory' — which is distinguishable from memory.read/search/list siblings because it implies graph traversal rather than record retrieval. However, 'hub-penalized multi-hop spreading activation' is unexplained jargon that adds obscurity rather than clarity, so it falls short of a 5.

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?

No indication of when an agent should choose this over memory.search, memory.hybrid_recall, memory.filter, or memory.aggregate, all of which could plausibly return related memories. There are no stated preconditions, exclusions, or alternative routing.

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