Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_agents_add_learning

Manually add a pattern, avoidance note, preference, or insight to an agent; high-confidence entries are injected into its system prompt to guide future behavior.

Instructions

Manually add a learning/insight to an agent. High-confidence learnings are injected into the agent's system prompt.

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": {
      "agent_id": "<agent_id>",
      "type": "<type>",
      "content": "<content>"
    },
    "name": "kernel_agents_add_learning"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesLearning type: pattern (observed), avoid (don't do), prefer (do this), insight (general)
scopeNogeneral = applies to every project; project (default when your run has a project) = only this project
contentYesThe learning content
agent_idYesAgent ID
confidenceNoConfidence 0-1 (default: 0.7)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose the key downstream effect — high-confidence learnings get injected into the agent's system prompt — which is genuinely valuable. But it leaves open what threshold counts as 'high confidence', whether entries are deduplicated or overwritten, and what the call returns.

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?

Two short sentences, the action first and the consequence second, with no filler. Every clause adds information an agent would otherwise have to guess.

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?

There is no output schema and no annotations, so the description is the only source of behavioral context. It covers the write and its system-prompt effect but omits return shape, deduplication behavior, and the effective confidence cutoff — gaps that matter for a mutation tool with five parameters.

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%, with enums documented for type and scope, so the schema already explains every parameter. The description only echoes the concept of confidence ('high-confidence') without adding format, threshold, or defaulting detail beyond the schema.

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 states a specific verb and resource: 'Manually add a learning/insight to an agent.' The word 'Manually' distinguishes it from implicit/automatic learning capture, though it never names a sibling such as kernel_agents_memory or kernel_agents_feedback.

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?

'Manually add' implies the caller is deliberately recording a lesson rather than relying on automatic capture, which is useful implied usage. However there is no explicit when-to-use/when-not guidance and no pointer to an alternative tool for reading or updating existing learnings.

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

Deploy Server

Other Tools