Skip to main content
Glama

memory_distill

Extracts insights from existing memories using an LLM rewriter in batch mode, with dry-run previews, configurable batch size, and memory-type filters.

Instructions

Extract insights from existing memories via LLM rewriter (batch mode).

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": "memory_distill"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNoPreview candidates without storing (default: true)
batch_sizeNoMax memories to process per run
memory_typesNoMemory types to process (default: observation, decision, reference, learning)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

C2.9/5.0
Behavior2/5

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

Annotations supply only destructiveHint=false, so the description carries the behavioral burden and largely drops it. It does not say whether new memories are written alongside or instead of the source ones, whether source memories are modified, what the LLM cost/latency looks like, or that the default is a non-storing preview. 'Batch mode' hints at scale but nothing actionable.

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?

A single front-loaded sentence with no filler. It is efficient, though its brevity is part of why the behavioral and usage information is missing, and the trailing space/parenthetical is slightly awkward.

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?

With no output schema and only a weak destructiveHint annotation, the description should explain what distillation produces and how candidates are reviewed before storing. Instead it omits return/result semantics and the consequence of running with dry_run=false, which is the risky path for a tool that generates new memory content.

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 all three parameters (dry_run, batch_size, memory_types) are already fully documented with defaults. The description adds only the loose phrase 'batch mode' and no semantics beyond the schema, so the baseline of 3 applies.

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?

States a specific verb ('extract insights') on a specific resource ('existing memories') and names the mechanism ('LLM rewriter, batch mode'). It is clear what the tool does, but it gives no signal distinguishing it from neighbors like memory_consolidate, memory_harvest, or memory_quality, which plausibly overlap.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no exclusions, and no named alternative. An agent cannot tell from the description whether to reach for memory_distill versus memory_consolidate or memory_quality, nor what preconditions (existing memory volume, quality state) make it appropriate.

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