Skip to main content
Glama
reflex-brain

reflex-brain

by dokiromboide

reflex_propose_lesson

Propose a new lesson or update by analyzing session messages, helping agents capture reusable knowledge from past interactions for continual learning.

Instructions

Propose a new lesson or update from session analysis

Input Schema

NameRequiredDescriptionDefault
tagsNo
topicYesTopic for the lesson
contentNoExplicit lesson content, instead of session extraction
confidenceNo
session_idNoSession ID to analyze
session_messagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

C2.4/5.0
Behavior2/5

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

With no annotations, the description carries the full burden, and it reveals almost nothing: it doesn't say whether the proposal is pending review or auto-applied, whether it is a write that persists anything, what happens if both content and session_messages are supplied, or how confidence affects outcome. The word 'Propose' hints at a non-committal write, but that is inference, not disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no filler and the action front-loaded, which is good structurally. But it is undersized for a 6-parameter tool with two mutually exclusive input modes, so the brevity reflects omission rather than economy.

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?

For a 6-parameter creation tool with an anyOf branch, no annotations, and no output schema, the description is far too thin. An agent lacks the semantics of the two input modes and any indication of what a successful proposal yields.

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 coverage is 50%, so the description needs to compensate and largely does not. The 'from session analysis' phrasing weakly signals the session_messages/session_id path, but the critical anyOf constraint (either content or session_messages required) and the role of confidence and tags are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action ('Propose') and resource ('a new lesson or update') with the input source ('from session analysis'), which is more than a tautology. However, it doesn't clarify what a 'proposal' is in this system (queued for review? immediately applied?) or how it differs from siblings like reflex_remember or reflex_list_proposals.

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?

No when-to-use guidance, no preconditions, and no named alternatives. An agent cannot tell from the description whether to propose a lesson here versus storing knowledge via reflex_remember or running reflex_research.

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