Skip to main content
Glama
Sign In
open-memex

open-memex

by stoneskin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

memory_list

Read-only

List stored memories newest first as a numbered inventory, filter by scope, type, or limit, and switch to an audit view to inspect active or all entries.

Instructions

List memories in a scope, newest first, as a numbered inventory. Each line keeps the raw fields — [type] id=… created=… source=… — say them back to the user in plain words (source=user → 'you told me this'; inference → 'I inferred this, check me'; keyword → 'caught from your own wording'), never read the raw id aloud unless they ask. When the user asks 'what do you remember about me?', use scope=both and present the inventory conversationally. The user may point at an entry by its number ('delete #3'): numbers are only valid for the listing you just produced — re-run memory_list, read the candidate back in full, and get a confirmation before calling memory_forget (deletion is permanent). include=all is the audit view (superseded versions, retracted, archived also shown). type filters to one memory type; limit caps how many entries come back.

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_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoOnly list memories of this type. Closed taxonomy — a misspelled type is rejected, never silently empty.
limitNoMax entries to list, newest first (default 20).
scopeNoWhich scope(s) to list. `project` = tied to this repo. `personal` = global across all your projects. `both` lists each scope's newest. Default: project.
includeNoD68: `active` (default) shows what is currently remembered — newest version of each fact, retracted/archived hidden. `all` is the audit view: every stored row including superseded versions and hidden ones. The default CHANGED in D68: superseded versions no longer appear unless include=all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.2
    • changedInput schema / properties / type / description
      Previous value: -"Only list memories of this type (e.g. decision, preference, gotcha)."New value: +"Only list memories of this type. Closed taxonomy — a misspelled type is rejected, never silently empty."
    • addedInput schema / properties / type / enum
      Added value: +[
+  "fact",
+  "preference",
+  "decision",
+  "constraint",
+  "todo",
+  "knowledge",
+  "howto",
+  "gotcha",
+  "lesson",
+  "observation",
+  "reference"
+]
  2. Changed3 schema fields changedv0.7.3
    • addedInput schema / properties / limit / description
      Added value: +"Max entries to list, newest first (default 20)."
    • changedInput schema / properties / scope / enum
      Previous value: -[
-  "project",
-  "personal",
-  "user",
-  "both"
-]New value: +[
+  "project",
+  "personal",
+  "both"
+]
    • addedInput schema / properties / type / description
      Added value: +"Only list memories of this type (e.g. decision, preference, gotcha)."
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover read-only and closed-world, yet the description adds genuinely non-obvious behavior: entry numbers are ephemeral and only valid for the listing just produced, raw ids should not be surfaced, deletion is permanent, and include=all is an audit view including superseded/retracted/archived rows. That is exactly the extra context annotations cannot carry.

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 action and output format, then the operating rules; nearly every clause earns its place. Minor redundancy in restating include=all both in the narrative and again in the schema, and the human-facing presentation rules make it longer than a pure API description would need.

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?

A read-only list tool with no output schema, four fully documented optional parameters, and description text covering ordering, default scope, the display contract, and the follow-on deletion flow. An agent has everything needed to call it and to present the result correctly.

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 baseline would be 3, but the description adds usage-level meaning: scope=both is prescribed for the 'what do you remember' case, include=all is framed as the audit view, and type is described as a single-type filter. It does not add syntax or format detail beyond the schema, hence not a 5.

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?

States a specific verb and resource ('List memories in a scope') plus ordering ('newest first') and output shape ('numbered inventory'). The 'what do you remember about me?' framing makes the inventory mode distinct from a query tool, but the nearest sibling memory_search is never named, so differentiation from it is left implicit.

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?

Gives explicit triggers ('when the user asks what do you remember about me, use scope=both'), explicit exclusions ('never read the raw id aloud unless they ask'), and a concrete hand-off rule to memory_forget with a re-run-plus-confirmation precondition. Nothing about when to pick this tool is left to inference.

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