MemScope

List memories

list_memories

Read-onlyIdempotent

Use this when the person wants to see what MemScope holds or find a memory to change: newest first, with id, one-line preview, scope, sensitivity, review state and date. Page with next_cursor. Not for answering a question (use search_memories) or reading one memory in full (use get_memory).

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": "list_memories"
  }
}

Input Schema

Name	Required	Description
`kind`	No	Only this kind.
`agent`	No	Only this agent's.
`limit`	No	Items to return, 1-100 (default 20).
`cursor`	No	The previous call's `next_cursor`, to page to older memories.
`filter`	No	'mine' (authored by the person), 'needs_review' (every flagged memory they can read), 'team'/'project' (team- or project-scoped), 'forgotten' (soft-deleted; ids for restore_memory). Omit it for everything.
`run_id`	No	Only this run's.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

changedInput schema / properties / cursor / anyOf

Previous value: -[
-  {
-    "maxLength": 64,
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 96,
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

First observedNov 7, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the description only needs to add context beyond that, which it does by disclosing sort order, the shape of each row, and the cursor-based paging mechanism. It does not mention default page size or that the 'forgotten' filter surfaces soft-deleted records, but those are covered in the schema.

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?

Two sentences, front-loaded with the trigger condition, then the output shape, then the exclusions with named alternatives. Every clause carries information an agent needs; nothing is padded.

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?

An output schema exists and annotations cover safety, so the description needn't restate return values in depth, and it already sketches them briefly. For a six-parameter, fully-documented filter tool, 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.

Parameters3/5

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

Schema description coverage is 100%, so the schema already explains kind, agent, limit, cursor, filter, and run_id. The description only echoes the paging parameter (next_cursor) and the result fields, adding little semantic meaning beyond the structured fields; baseline 3 applies.

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 gives a concrete verb and resource (listing memories), and specifies ordering (newest first) plus the exact fields returned (id, one-line preview, scope, sensitivity, review state, date). It explicitly distinguishes itself from search_memories and get_memory, so an agent can tell the three apart without opening a schema.

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?

It states both when to use it ('the person wants to see what MemScope holds or find a memory to change') and when not to, naming the correct alternatives for each excluded case. No inference is required to route between list, search, and get.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All MemScope tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?