Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis · Memory Curator — Set Working Memory

set_working_memory

Stores a key/value pair in the current session's ephemeral working memory, helping agents keep mid-pipeline state, intermediate results, and decisions accessible during a run.

Instructions

Write a key/value pair to the current session's working memory.

Working memory is an ephemeral scratchpad — it persists for the session
but is not indexed for vector search. Use it for state that agents need
mid-pipeline (e.g. intermediate results, decisions made so far).

Args:
    session_id: Pipeline session ID from session_bootstrap().
    key: Variable name (e.g. 'current_article', 'user_intent').
    value: Value to store (any string, JSON, or text).

Input Schema

NameRequiredDescriptionDefault
keyYes
valueYes
session_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Discloses key behavioral traits: ephemeral, session-only persistence, no vector search indexing. Since no annotations exist, the description fully covers behavior. Could mention whether existing keys are overwritten or the value scope size limits.

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-structured with a concise paragraph followed by bulleted arguments. No redundant sentences. Could be slightly more concise by removing 'any string, JSON, or text' redundancy, but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the tool's purpose, usage context, and parameter meanings. With an output schema present, return values need not be explained. Lacks usage examples or edge cases, but sufficient for a simple write operation.

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 has 0% description coverage, so the description compensates by explaining each parameter: session_id as pipeline session ID, key as variable name with examples, value as any string/JSON/text. Adds meaning beyond schema titles.

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 writes a key/value pair to working memory, specifying the action ('write') and resource ('working memory'). It distinguishes from sibling tools like 'get_working_memory' and 'remember' by emphasizing ephemeral, session-scoped storage not indexed for search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use for state needed mid-pipeline (intermediate results, decisions). Contrasts with vector search, implying when not to use (for persistent or searchable data). Provides clear context but could state exclusions more directly.

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