Skip to main content
Glama

run_promote

Destructive

Consolidates L1 memories into L2 scenario summaries and promotes stable L2 memories into L3 persona rules; run deduplication first to avoid duplicate scenarios.

Instructions

Run the promote pipeline: consolidates atomic L1 memories into L2 scenario summaries, and promotes stable L2 memories into L3 core persona rules. Requires L1 memories to exist; run run_dedup first so near-duplicates don't become separate scenarios. Source memories are archived to L0 after promotion (not deleted). A maintenance step, not a substitute for run_decay. Mutates the store, is not idempotent, and requires agent auth when the agent has a registered key. Returns promoted/consolidated/merged/source counts.

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": "run_promote"
  }
}

Input Schema

NameRequiredDescriptionDefault
min_l1NoMinimum L1 memories to consolidate into L2 (default: 3)
min_l2NoMinimum L2 memories to promote to L3 (default: 2)
api_keyNoAPI key for agent authentication (required if agent has a registered key)
agent_idNoID of the requesting agentunknown
namespaceNoNamespace to scan (currently the promote pipeline scans all namespaces)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description qualifies the destruction: sources are archived to L0, not deleted. It also discloses the auth requirement when an agent has a registered key. It restates the idempotency hint, which is minor redundancy rather than added value.

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?

Front-loads purpose before prerequisites and caveats, with minimal waste. The closing clause "Mutates the store, is not idempotent" largely repeats annotations, costing a little density.

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

Completeness5/5

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

Covers preconditions, ordering, data disposition (archived to L0), auth needs, and the return payload (promoted/consolidated/merged/source counts), which compensates for the missing output schema. An agent has everything needed to invoke it correctly.

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 description coverage is 100%, so min_l1/min_l2 thresholds, api_key, agent_id, and namespace are already documented in the schema. The description adds no threshold semantics or interaction details beyond what the schema states, so the baseline 3 applies.

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 plus the exact transformation performed (L1 atomic → L2 scenario summaries, L2 → L3 persona rules), which lets an agent understand the pipeline stage precisely. Siblings run_dedup and run_decay are named as distinct steps, so it is unambiguous in the tool set.

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?

Explicit preconditions ("Requires L1 memories to exist") and an explicit ordering instruction ("run run_dedup first so near-duplicates don't become separate scenarios"). It also carves out scope against run_decay with "not a substitute for run_decay".

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