Skip to main content
Glama

plur_learn

Record a reusable knowledge assertion—a learning, preference, or correction—with tags, scope, and commitment level for your AI agent's long-term memory.

Instructions

Create an engram — record a reusable learning, preference, or correction. Multi-agent note: in an orchestration that spawns subagents, have the PARENT session own plur_learn writes — spawned subagents should return their findings as text for the parent to persist, rather than each calling plur_learn (tool availability is not guaranteed in every subagent context). See plur-ai/plur#281.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoSearchable keyword tags — contribute to BM25/embedding recall, so concrete keywords pay off
typeNoCategory of the engram
scopeNoNamespace, e.g. global, project:myapp
domainNoDomain tag, e.g. software.deployment
pinnedNoAlways-load flag. If true, this engram bypasses the keyword-relevance gate at injection time. Use sparingly: meta-rules, safety conventions, core operating principles only.
sourceNoOrigin of this knowledge (URL, conversation ref, etc.)
rationaleNoWhy this knowledge matters — also enters the search corpus, helps recall by intent not just statement
statementYesThe knowledge assertion to store
commitmentNoHow firmly the user has committed to this belief (default: leaning)
supersedesNoEngram IDs this statement intentionally replaces (#240). Writes relations.supersedes on the new engram and the reverse superseded_by edge on each local target. Supersedes-linked pairs are skipped by tension scans — an intentional update is not a contradiction. Use when updating a standing fact (new version, changed rule) rather than contradicting it.
valid_fromNoISO date (YYYY-MM-DD) the knowledge becomes valid — inject/recall skip the engram before this date (#347)
valid_untilNoISO date (YYYY-MM-DD) the knowledge expires — inject/recall skip the engram after this date. Set this for any time-bound fact (offers, deadlines, temporary endpoints). When omitted, an explicit expiry phrase in the statement ("valid until 31 May 2026") is auto-parsed and echoed back (#347)
locked_reasonNoWhy this engram is locked (only meaningful when commitment=locked)
Behavior3/5

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

Annotations already indicate not idempotent (idempotentHint: false) and not destructive (destructiveHint: false). The description adds value with the multi-agent context but does not elaborate on other behavioral traits such as side effects or rate limits. The description does not contradict annotations.

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?

The description is two sentences plus a reference, front-loading the main action and then providing critical multi-agent guidance. Every sentence earns its place without redundancy.

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 the tool's 13 parameters and no output schema, the description covers the core purpose and provides crucial multi-agent context. However, it does not hint at the return value (e.g., engram ID), which is a minor gap. Overall, it is fairly complete.

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 100% (all 13 parameters have descriptions in the input schema). The description does not add extra meaning beyond what the schema provides. Baseline 3 is appropriate.

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 clearly states the tool's purpose: 'Create an engram — record a reusable learning, preference, or correction.' It uses a specific verb ('Create') and resource ('engram'), and the multi-agent note provides additional context that distinguishes it from sibling tools like plur_learn_batch.

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?

The description explicitly provides when-not-to-use guidance: in a multi-agent orchestration, spawned subagents should not call this tool; instead, they should return findings as text for the parent to persist. It also explains why (tool availability not guaranteed). This is exemplary usage guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/plur-ai/plur'

If you have feedback or need assistance with the MCP directory API, please join our Discord server