Skip to main content
Glama
Lyellr88

marm-memory

by Lyellr88
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

marm_compaction

Compact related memories into a single summary to reduce context bloat.

Instructions

Compact related memories into a single summary to reduce context bloat.

Workflow: status/candidates → stage → review → apply/discard

action="status"     — check if compaction candidates exist (run first)
action="candidates" — get pending candidates with source previews; each includes a ready-to-use prompt
action="stage"      — submit your summary: {candidate_id, suggested_summary}; source_memory_ids optional
action="review"     — inspect staged summaries before committing
action="apply"      — commit a staged summary; source memories are marked compacted
action="discard"    — reject a candidate, staged or not, without touching source memories

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
summariesNo
candidate_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.35.0
  2. Removedv2.25.0
  3. Changed6 schema fields changedv2.17.1
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / action / title
      Added value: +"Action"
    • addedInput schema / properties / candidate_id / title
      Added value: +"Candidate Id"
    • addedInput schema / properties / summaries / title
      Added value: +"Summaries"
    • addedInput schema / title
      Added value: +"marm_compactionArguments"
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "type": "object"
-}New value: +null
  4. First observedv2.14.1

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are provided, so the description must carry behavioral burden. It discloses key state effects: apply 'marks source memories compacted', discard 'without touching source memories', stage takes a summary object. It does not state permissions, reversibility of apply, or failure modes, so a 4 rather than 5.

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

Conciseness5/5

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

Front-loaded purpose sentence followed by a compact workflow line and a tight action-by-action list. Every line earns its place with no filler.

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

Completeness4/5

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

Given no output schema and no annotations, the description covers the lifecycle and key state effects well. It still leaves the 'summaries' parameter unexplained and doesn't describe what status/candidates return in enough detail, so not fully complete.

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

Parameters4/5

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 explains action semantics well, gives the stage payload shape ({candidate_id, suggested_summary}) and notes source_memory_ids is optional. However, the schema shows a 'summaries' array parameter that the description never explains, leaving a gap.

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?

States a specific verb+resource ('Compact related memories into a single summary') and the goal ('reduce context bloat'). Distinguishable from siblings like marm_distill or marm_summary by the candidate/stage/apply lifecycle it lays out.

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

Usage Guidelines5/5

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

Provides an explicit workflow sequence (status/candidates → stage → review → apply/discard), tells the agent to 'run first' for status, and describes each action's purpose. The when-to-use-which-action mapping is essentially complete.

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