Skip to main content
Glama
billy12151

memory-arbiter-mcp

by billy12151
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_govern

Resolve memory conflicts and duplicates with explicit authorization. Retire, merge, and manage workspaces in a shared SQLite store.

Instructions

Authorized governance: retire, merge near-duplicates, apply/replan/resolve conflicts, confirm, and manage workspaces.

Every state-changing action requires explicit user authorization for that action, then authorized=true. Workspace-mutating actions (confirm_pending_workspace, rename_workspace_canonical, migrate_workspace, separate_workspace_alias, move_memories_workspace) also require workspace — call memory_review(view="workspaces") first to list existing buckets. Call memory_govern(action="help") for exact actions, accepted fields, impact notes, and confirmation semantics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
actionNohelp

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.16.5
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "title": "memory_governDictOutput",
-  "type": "object"
-}New value: +null
  2. Addedv0.11.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden; it does disclose the authorization gate and the confirmation-semantics pointer, which is real value. However it says nothing about what retire/merge actually destroy, reversibility, or side effects, deferring impact notes to action="help" rather than stating them.

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?

Short and front-loaded with the governing action list, then prerequisites, then the help pointer. The hard-wrapped fragments break the sentences awkwardly but there is no filler content.

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?

For a high-complexity, multi-action tool with no annotations, no output schema and a freeform data object, the description leaves the agent unable to construct a real invocation without an extra action="help" round-trip. The deferral is explicitly documented, which is honest, but the definition is not self-sufficient.

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 coverage is 0% and `data` is an untyped freeform bag, so the description must compensate. It partially does by naming concrete action values (retire, confirm_pending_workspace, rename_workspace_canonical, migrate_workspace, separate_workspace_alias, move_memories_workspace) and by stating which actions need workspace, but accepted data fields are left entirely to the help call.

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 concrete family of governance verbs (retire, merge near-duplicates, apply/replan/resolve conflicts, confirm, manage workspaces) rather than a tautology, so the agent knows this is the state-changing memory-curation surface. It stops short of a 5 because it never distinguishes itself from memory_repair or memory, which cover adjacent curation work.

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?

Gives actionable usage rules: every state-changing action needs explicit user authorization plus authorized=true, workspace-mutating actions need workspace, and the agent should list buckets via memory_review(view="workspaces") first. It lacks any when-not-to-use or sibling-choice guidance, keeping it below 5.

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

Deploy Server

Other Tools