Skip to main content
Glama
billy12151

memory-arbiter-mcp

by billy12151

memory_review

Inspect stored memories before accepting or rejecting changes. Review conflicts, histories, and entity states to decide which version to apply.

Instructions

Read-only inspection: overview, doctor, conflicts, conflict_detail, history, expired, audit, entities, help.

Use memory_review(view="help") for accepted fields. Inspect conflict_detail before judging a conflict so its members, value groups, revision, and apply state are visible.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
viewNohelp

Schema Changelog

Changes observed during successful MCP inspections.

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

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and explicitly declares the tool is read-only, which is a key safety trait. It also reveals workflow expectations around conflict_detail. It stops short of describing output shape or error behavior, but the read-only disclosure is strong enough to avoid misuse.

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 compact and each sentence adds distinct value: scope, field discovery, and conflict judgment guidance. The list of view names is dense, but not padded with filler.

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 description compensates partially by pointing to view='help' for accepted fields and giving conflict workflow guidance. However, with no output schema and no annotation coverage, the unexplained data parameter and the meaning of individual views leave a real gap for an agent that has only this text to work from.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate, but it only gives meaning for the 'view' parameter (view='help') and leaves 'data' completely unexplained. The agent still cannot infer what values data accepts or how it interacts with views.

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?

The description opens with a specific verb and scope ('Read-only inspection') and enumerates the exact set of views the tool exposes. This clearly distinguishes it from the mutating sibling tools memory_govern and memory_repair.

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?

It gives concrete operational guidance: call view='help' to discover accepted fields and inspect conflict_detail before making a judgment about a conflict. It does not explicitly name sibling tools as alternatives, but 'read-only' makes the intended use context clear.

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