Cachly — AI Cognitive Brain

global_learn

Store a reusable lesson that applies across all projects. If a lesson with the same topic already exists, it updates in place to prevent duplicates.

Instructions

Store a lesson that applies across ALL your projects (cross-project knowledge). Idempotent: if a lesson with the same topic already exists, it is updated in place — no duplicates are created. Returns a confirmation with the stored lesson key. No rate limits. Global lessons are stored with the prefix cachly:global:lesson: and recalled from any instance via global_recall. Use for tool preferences, personal workflows, platform quirks, and universal gotchas. Example: global_learn(topic="bash:macos-arrays", lesson="Arrays work differently on macOS bash 3.2"). Use learn_from_attempts for project-specific session lessons; use team_learn to share lessons with your team.

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": {
      "instance_id": "<instance_id>",
      "topic": "<topic>",
      "lesson": "<lesson>"
    },
    "name": "global_learn"
  }
}

Input Schema

Name	Required	Description
`tags`	No	Optional tags
`topic`	Yes	Topic key in format "category:keyword"
`lesson`	Yes	The lesson content
`severity`	No	Severity (default: minor)
`instance_id`	Yes	UUID of the cache instance (used for connection)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Apr 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

No annotations provided, so description carries full burden. It discloses idempotency, prefix storage (cachly:global:lesson:), global recall via global_recall, no rate limits, and return type (confirmation with key). This fully covers behavioral traits.

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?

Description is efficient but somewhat long (5 sentences). Front-loaded with purpose and key behaviors. Every sentence adds value, though could be tightened slightly.

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?

Given 5 parameters, no output schema, and many siblings, description covers all essential context: idempotency, storage location, recall method, usage guidelines, example, and parameter format hints. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds context beyond schema: provides example topic format ('category:keyword'), explains instance_id purpose (though not necessary), and gives a usage example. Adds meaningful context.

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 stores cross-project lessons, with specific verb 'Store' and explicit resource 'lesson that applies across ALL your projects'. It distinguishes from siblings by naming learn_from_attempts and team_learn with their specific use cases.

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 states when to use this tool and when to use alternatives: 'Use learn_from_attempts for project-specific session lessons; use team_learn to share lessons with your team.' It also notes idempotency and global recall.

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

Deploy Server