Skip to main content
Glama

memory_record

DestructiveIdempotent

Record, correct, or disable candidate methods, failures, and preferences for LAMMPS tasks. Service measurements create verified memories, and disabling a validation memory suspends plan reuse.

Instructions

Save a candidate method/failure/preference, correct it, or disable it. Service measurements create verified memories. action: record, correct, disable. Disabling a validation memory also suspends reuse of that plan.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_id": "<task_id>",
      "revision": "<revision>",
      "title": "<title>",
      "summary": "<summary>",
      "kind": "<kind>",
      "op_id": "<op_id>"
    },
    "name": "memory_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
filesNo
op_idYes
titleYes
tokenNo
actionNorecord
reasonNo
summaryYes
task_idYes
revisionYes
memory_idNo
conditionsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior4/5

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

The annotations already declare this a mutating, destructive, idempotent operation, so the safety profile is largely covered. The description adds real value beyond them by disclosing a non-obvious side effect: disabling a validation memory also suspends reuse of that plan. It stops short of 5 because permissions or how correction interacts with existing revisions are not described.

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 tight sentences, front-loaded with the core capability and the action list. Slightly dense but no filler sentences.

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

Completeness3/5

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

The output schema exists, so return values needn't be explained. Still, for a 12-parameter, 6-required mutation tool with zero schema coverage, the description leaves the agent guessing about key parameters like op_id, revision, memory_id, and task_id.

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% across 12 parameters, so the description must compensate, and it only explains the 'action' enum values. Required fields like task_id, revision, op_id, kind, title, and summary, plus memory_id for correction, receive no explanation at all.

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 names specific verbs (save, correct, disable) and the resource (candidate method/failure/preference memories), and it enumerates the action values. It falls short of 5 because it never distinguishes itself from siblings like memory_search, memory_get, or memory_rebuild.

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

Usage Guidelines3/5

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

It implies usage by noting that 'service measurements create verified memories,' which suggests this tool handles unverified candidates, and it lists the three action values. However, there is no explicit when-to-use/when-not guidance and no routing to alternatives for reading or searching memories.

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