Skip to main content
Glama
Sign In
open-memex

open-memex

by stoneskin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

memory_workingstate

Capture, read, or clear an ephemeral per-project working-state note so a fresh session can resume interrupted work without replaying context.

Instructions

Read, write, or clear the one ephemeral per-project working-state note (§3.6, D89): where an interrupted task stands, so a fresh session can resume. Scratch state, NOT durable knowledge — it never enters memory retrieval or a review ladder; any conclusion here that should outlive the task goes through the normal memory_add/checkpoint-proposal path instead. WRITE it (action=write, content required) when the user signals the session or task is wrapping up — body rubric: task summary (one paragraph), open files, last commands, where the work stands, next step; short by design, a scratch note, not a transcript. READ it when resuming work or when the user asks what they were doing. CLEAR it on the user's request only. The note lives outside memories/, the user can edit the plain file directly, and it expires after ttl_days (default 7) — expired notes are ignored and audit reports them.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "memory_workingstate"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoread = show the current note (empty when none); write = create or refresh it; clear = delete it.read
contentNoNote body, Markdown, short by design (required for write). Rubric: task summary (one paragraph), open files, last commands, where the work stands, next step. A scratch note, not a transcript.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.9.0

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations, it discloses that the note lives outside memories/, is user-editable as a plain file, and expires after ttl_days (default 7) with expired notes ignored and reported by audit. The only residual tension is that clear deletes a note while destructiveHint=false, though for a disposable scratch file this is reasonable rather than contradictory.

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?

Front-loaded with the core definition, then per-action guidance, then lifetime details; every sentence carries information. Slight redundancy in restating the body rubric that already appears in the content schema costs it a point.

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 two-parameter, non-destructive tool with no output schema, the description covers purpose, per-action triggers, storage location, editability, expiry behavior, and the escalation path to durable memory. 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.

Parameters4/5

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

Schema coverage is 100%, so the action enum and content rubric are already documented. The description still adds gating semantics — content required for write, clear only on user request — and frames the note as short by design rather than a transcript, which reinforces how much to pass.

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 first sentence names the specific verbs and the exact resource: an ephemeral per-project working-state note for resuming interrupted tasks. It immediately distinguishes this from durable memory by stating the note never enters retrieval or a review ladder.

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?

Explicit triggers per action: write when the user signals wrapping up, read when resuming or when asked what they were doing, clear only on user request. It also names the alternative route (memory_add / checkpoint proposal) for anything that should outlive the task.

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