Skip to main content
Glama
billy12151

memory-arbiter-mcp

by billy12151
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_repair

Repair and maintain memory integrity: rebuild evidence, scan conflicts, remove duplicates, clean history, replay backups, and manage advisory notices.

Instructions

Maintenance: evidence rebuild, conflict scans (scheduled-task spec under help topic scheduled_tasks), full-library duplicate sweeps (scan_duplicates), history cleanup, entity assignment, pending activation, backup replay, notices, and semantic runtime control.

Use memory_repair(task="help") for notice handling and semantic_control actions. Semantic notices are advisory; read both memories before dismiss or resolve, and never pass a notice directly to judge or resolve_conflict.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
taskNohelp

Schema Changelog

Changes observed during successful MCP inspections.

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

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the behavioral burden. It discloses that semantic notices are advisory and warns to read both memories before dismiss/resolve, which is valuable. Yet most maintenance operations like history cleanup and backup replay are not described in terms of destructiveness, reversibility, or side effects.

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 information-dense, with the maintenance category and action list front-loaded. The second sentence adds crucial handling guidance without unnecessary filler. It is slightly list-heavy but earns its place.

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

Completeness2/5

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

This is a broad maintenance tool with no annotations and no output schema, so the description must supply enough context for correct invocation. It does not explain how to invoke most tasks, what data they require, or what they return. The reference to a help topic is useful but not sufficient for the full scope.

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 explain both parameters. It mentions task='help' and implies various task actions, but the data parameter is entirely unexplained. An agent cannot determine what payload is needed for most listed maintenance tasks.

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 clearly identifies memory_repair as a maintenance tool and enumerates concrete operations (evidence rebuild, conflict scans, duplicate sweeps, history cleanup, etc.). It distinguishes itself from review/govern siblings by the 'Maintenance' category, though the long list makes the primary purpose somewhat diffuse.

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 explicitly says to use memory_repair(task='help') for notice handling and semantic_control actions, and gives a clear exclusion: never pass a notice directly to judge or resolve_conflict. However, it does not broadly state when to prefer memory_repair over memory_review, memory_govern, or memory.

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