Skip to main content
Glama
billy12151

memory-arbiter-mcp

by billy12151
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_govern

Govern shared memory by retiring entries, merging duplicates, resolving conflicts, and managing workspaces—all with explicit user authorization for each action.

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. 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

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It discloses the key authorization requirement and points to help for impact notes and confirmation semantics, but stops short of describing what actions actually destroy or modify, or what side effects occur. It adds some transparency but leaves major behavioral details to the help action.

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?

The description is short, front-loaded with the main purpose, and every sentence is informative. The instruction to call help is valuable and placed at the end. It loses a point for slightly dense wording and lack of bullet structure, but remains above average.

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?

This is a complex multi-action governance tool with no output schema, no annotations, and bare parameters. The description acknowledges its own incompleteness by directing users to action='help' for exact details. This is a workable pattern but not fully complete; it relies on an extra step, leaving gaps for an agent that might attempt a call without first consulting help.

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%, so the description must compensate. It adds meaning by explaining that 'action' selects the operation (with default 'help') and that 'authorized=true' is required in data for state changes. However, it defers exact accepted fields and action values to the help action, so it only partially compensates.

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 specific governance verbs ('retire', 'merge near-duplicates', 'apply/replan/resolve conflicts', 'confirm', 'manage workspaces') that clearly indicate a memory governance tool. It does not explicitly contrast with sibling tools like memory_review or memory_repair, but the action list conveys a distinct maintenance function beyond review/repair.

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

Usage Guidelines3/5

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

It implies this tool is for state-changing memory operations by stating 'Every state-changing action requires explicit user authorization...' and lists mutation-like actions. However, it never explicitly says when to use memory_govern versus siblings, and provides no 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.

Deploy Server

Other Tools