Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis — Record Persona Learning

record_persona_learning

Save confirmed behavioural rules and preferences so Metis applies them in future sessions. Record corrections, workflow choices, and avoids that should persist beyond the current conversation.

Instructions

Record a lasting lesson about how Metis should behave, so it survives the session.

Use this when the researcher corrects how something should be done, states a preference
between real alternatives, or confirms an approach — anything that should change
Metis' behaviour in FUTURE sessions rather than only this one.

This is what makes the persona grow. Metis' memory already accumulates facts
about the work; without this, none of it changed how she behaves. A correction
that is only remembered as having happened is not learned.

WHAT BELONGS HERE:
  - "Prefers the explicit mark-read button over auto-marking" (a real choice)
  - "Wants feed URLs verified live before being added" (a workflow rule)
  - "Do not use ANSI colour; emoji survive copy-paste" (an avoid)

WHAT DOES NOT:
  - Facts about the research or the code — that is memory (`remember`,
    `save_session_summary`).
  - One-off task details that will not recur.
  - Anything the researcher has not actually confirmed. Do not record an inference as a
    lesson; if unsure whether it is durable, ask, or leave it.

Args:
    lesson: The behavioural rule, stated imperatively and briefly — how Metis
        should act from now on. One or two sentences.
    category: One of voice, workflow, preference, avoid, domain.
    evidence: Why this is believed — quote or paraphrase what the researcher said, and
        when. An unexplained rule cannot be audited later.
    supersedes: Optional. Text from an earlier lesson this replaces, so the
        older one is marked rather than silently contradicted.

Returns:
    Confirmation, and how many lessons are now on record.

Input Schema

NameRequiredDescriptionDefault
lessonYes
categoryNopreference
evidenceNo
supersedesNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.8/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does well: it explains that the record persists across sessions, grows the persona, requires researcher confirmation, and marks superseded lessons rather than silently contradicting them. It does not describe permissions, retention/deletion behavior, or failure modes, so it is strong but not fully exhaustive.

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 definition is front-loaded with the action and persistence rule, then structured into triggers, inclusions, exclusions, and parameter guidance. Although detailed, the length is justified by the tool's behavioral complexity and the examples earn their place.

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?

For a four-parameter, no-annotation, persistent-memory mutation tool, the description covers purpose, when to use it, when not to use it, parameter meaning, evidence requirements, superseding behavior, and return shape. The output schema covers the return format, so no critical context is missing.

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

Parameters5/5

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

Schema coverage is 0%, but the description compensates fully: it documents lesson, category, evidence, and supersedes. It supplies the category enum values (voice, workflow, preference, avoid, domain), explains the imperative style of lesson, and describes evidence as an auditable quote or paraphrase with timing.

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 opens with a specific verb and resource: 'Record a lasting lesson about how Metis should behave.' It distinguishes this from ordinary memory by saying the lesson must survive the session and change future behavior, which an agent can use to tell it apart from siblings like remember or save_session_summary.

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 gives explicit triggers: corrections, stated preferences between real alternatives, and confirmed approaches. It also states exclusions under 'WHAT DOES NOT' and names the sibling memory tools that should be used for research/code facts instead.

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