Skip to main content
Glama

Metis · Memory Curator — Remember

remember

Store findings, concepts, or workflows in Metis memory with automatic classification and scope tags, enabling later retrieval via recall.

Instructions

Store something in memory with automatic classification and scope tagging.

The unified write interface to Metis's memory system. Classifies the content
into the appropriate memory layer and stores it with scope tags for later
retrieval via recall().

Memory types:
  - 'episodic': A time-stamped event (something that happened)
  - 'semantic': A distilled concept or definition (timeless knowledge)
  - 'procedural': A workflow or how-to pattern
  - 'note': A human-curated memory palace entry (saved to DB + markdown)
  - 'auto': Let Metis classify based on content (default)

Scope tags determine visibility:
  - scope='global': Visible to all agents and projects
  - scope='agent': Visible only when agent_id matches
  - scope='project': Visible only when project_id matches
  - scope='session': Visible only in this session

Args:
    content: The text to remember. Can be a finding, concept, workflow,
        decision, or any text worth preserving.
    memory_type: How to classify this memory. One of 'episodic', 'semantic',
        'procedural', 'note', or 'auto' (default — Metis decides).
    agent_id: Tag this memory as belonging to a specific agent (e.g. 'librarian').
    project_id: Tag this memory as belonging to a specific project.
    scope: Visibility scope: 'global' (default), 'agent', 'project', or 'session'.
    title: Optional short title. Auto-generated from content if empty.
    tags: Comma-separated topic tags (e.g. 'malaria,diagnostics,rdts').
    session_id: Current pipeline session ID (optional).

Returns:
    Confirmation of what was stored, in which layer, with what scope.

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": {
      "content": "<content>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNo
scopeNoglobal
titleNo
contentYes
agent_idNo
project_idNo
session_idNo
memory_typeNoauto

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.4

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description does the heavy lifting well: it discloses that classification is automatic ('auto' default), that scope controls visibility by agent/project/session, that 'note' type has a side effect ('saved to DB + markdown'), and what the call returns. Missing only edge-case behavior such as duplicate handling or whether existing memories are overwritten.

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?

Well front-loaded (purpose in sentence one) and organized under clear headings, but the memory-type list and scope list each appear twice — once in the reference lists and again in the Args block — adding roughly ten lines of redundant text.

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?

Complete for an 8-parameter write tool: it supplies purpose, taxonomy, scope semantics, per-parameter meaning, a tag format example, and return shape (redundant with the output schema, but harmless). Nothing an agent needs in order to call it correctly 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 description coverage is 0% across 8 parameters, and the Args block fully compensates: every parameter gets meaning plus origin beyond its title, including enumerated values for memory_type and scope, scope visibility semantics, a tag format example ('malaria,diagnostics,rdts'), and defaults stated in prose.

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?

Opens with a specific verb + resource ('Store something in memory with automatic classification and scope tagging') and frames itself as 'The unified write interface to Metis's memory system', which implicitly separates it from the type-specific stores (store_episodic_memory, store_semantic_memory) and names recall() as its read counterpart. It never explicitly names those siblings, so the differentiation is inferential rather than stated.

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?

Usage context is clear for the primary case ('content ... can be a finding, concept, workflow, decision, or any text worth preserving') and recall() is given as the retrieval path. However, with ~12 sibling memory-writing tools in the namespace, an agent gets no explicit when-not guidance or routing rule telling it to prefer this over add_memory_entry or the layer-specific store_* tools.

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