Skip to main content
Glama

Run NOCTURNE consolidation

padam_sleep
Destructive

Run a scheduled consolidation cycle to move buffered episodes into semantic memory, guard against over-weighting rare dramatic episodes, and use dry_run to preview changes.

Instructions

Run a consolidation cycle: move episodes from the buffer into semantic memory with safeguards against over-weighting rare dramatic episodes. This can create records and replace older versions; replaced versions stay in history. Normally scheduled, not called by hand. Use dry_run to see the sample first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "padam_sleep"
  }
}

Input Schema

NameRequiredDescriptionDefault
remNoAlso run Active REM Sleep graph consolidation, duplicate compression, and local insight synthesis
batchNo
scopeNoOptional scope restriction for REM graph dreaming
dry_runNo
max_insightsNoMaximum number of new REM insights synthesized per cycle

Output Schema

NameRequiredDescriptionDefault
remNo
betaNo
noteNo
kindsNo
outcomesNo
cancelledNo
rolled_backNo
episodes_sampledYes
overreplay_shareNo
sampling_clustersNo
kind_entropy_ratioNo
high_priority_shareNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.6.2
    • addedInput schema / properties / max_insights
      Added value: +{
      +  "default": 4,
      +  "description": "Maximum number of new REM insights synthesized per cycle",
      +  "maximum": 20,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / rem
      Added value: +{
      +  "default": false,
      +  "description": "Also run Active REM Sleep graph consolidation, duplicate compression, and local insight synthesis",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "Optional scope restriction for REM graph dreaming",
      +  "maxLength": 200,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "beta": {
      +      "type": "number"
      +    },
      +    "cancelled": {
      +      "type": "boolean"
      +    },
      +    "episodes_sampled": {
      +      "type": "integer"
      +    },
      +    "high_priority_share": {
      +      "type": "number"
      +    },
      +    "kind_entropy_ratio": {
      +      "type": "number"
      +    },
      +    "kinds": {
      +      "type": "object"
      +    },
      +    "note": {
      +      "type": "string"
      +    },
      +    "outcomes": {
      +      "type": "object"
      +    },
      +    "overreplay_share": {
      +      "type": "number"
      +    },
      +    "rem": {
      +      "type": "object"
      +    },
      +    "rolled_back": {
      +      "type": "boolean"
      +    },
      +    "sampling_clusters": {
      +      "type": "integer"
      +    }
      +  },
      +  "required": [
      +    "episodes_sampled"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.4.8

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds genuinely new context: it can create records and replace older versions, and replaced versions remain retrievable in history. That reversibility detail is exactly what an agent needs before invoking a destructive mutation, though it says nothing about cost, runtime, or locking.

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?

Three front-loaded sentences: purpose first, then the mutation/history consequence, then the operating guidance. Every sentence carries weight, though the closing dry_run sentence could have been merged into the guidance clause.

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?

For a destructive, non-idempotent background-style tool with an output schema, the description covers what changes, what is preserved, and how to preview safely. The remaining gaps — effect of scope/batch, and expected duration — are secondary given the output schema exists.

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 60%, and the description only elaborates on dry_run ("see the sample first") and the general over-weighting safeguard. rem, batch, and scope get no explanatory treatment in the description beyond their own schema text, so it adds modest value over structured fields.

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 gives a specific verb and resource — run a consolidation cycle that moves episodes from the buffer into semantic memory — plus the distinguishing behavioral twist (safeguards against over-weighting rare dramatic episodes). An agent can tell this apart from padam_write and padam_confirm without opening any schema.

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?

"Normally scheduled, not called by hand" is an explicit when-not-to-use statement, and "Use dry_run to see the sample first" gives a concrete safe-path procedure. It stops short of naming a sibling alternative for the manual case, so it is clear context rather than full alternative routing.

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