STEM — Persistent AI Memory

List latest saved memories

list_memories

Read-onlyIdempotent

List this account’s saved memories in chronological order, newest-created first (saved timestamp, then ID). Use this for latest, newest or recent memories; use recall for relevant topics and read_memory for an exact ID. Follow nextCursor for older pages. A page is not the entire account; never guess memory IDs or infer absence from relevance search. No updated-time order is available.

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
`limit`	No	Page size, 1–50 (default 20).
`order`	No	Only saved-creation order is supported; updated timestamps are not recorded.
`cursor`	No	Opaque nextCursor from the previous page; omit for the latest page.

Output Schema

Name	Required	Description	Default
`order`	Yes
`hasMore`	Yes
`memories`	Yes
`nextCursor`	Yes
`timestampBasis`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 27, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, but the description adds real value beyond them: pagination via nextCursor, the fact that a page is not the whole account, and that no updated-time ordering exists. It stops short of describing result fields, though an output schema is present to cover that.

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 ordering guarantee and the disambiguation, then pagination caveats. Slightly redundant: 'No updated-time order is available' restates what the order parameter already documents, costing a tail sentence.

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 read-only, zero-required-parameter listing tool with a full output schema and rich annotations, the description covers the only genuinely ambiguous aspects: ordering, pagination and scope-of-page. Nothing an agent needs to invoke 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 coverage is 100% and each parameter carries its own description, so the schema already does the heavy lifting. The description only echoes the cursor behavior ('Follow nextCursor for older pages') and the absence of updated-time ordering, adding no syntax or semantics the schema lacks.

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?

States a specific verb and resource ('List this account's saved memories') plus a precise ordering guarantee (saved timestamp descending, then ID). It names the sibling tools it is not (recall, read_memory), so an agent can select it without opening any 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?

Explicitly routes the agent: use this for 'latest, newest or recent memories', use recall for 'relevant topics', read_memory for 'an exact ID'. It also warns against inferring absence from relevance search, which is a real failure mode for a listing tool.

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

All STEM — Persistent AI Memory 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?