MemScope

Remember (old name)

remember

Old name for save_memory; kept until 2027-01-07. Same arguments and results: see save_memory.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "content": "<content>"
    },
    "name": "remember"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No
`team`	No
`agent`	No
`scope`	No
`run_id`	No
`content`	Yes
`project`	No
`importance`	No
`supersedes`	No
`valid_until`	No
`idempotency_key`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedNov 9, 2026

removedInput schema / properties / agent / description
```
Removed value: -"Your agent label."
```

removedInput schema / properties / content / description

Removed value: -"One self-contained fact, decision or convention, up to 8000 characters."

removedInput schema / properties / idempotency_key / description

Removed value: -"Optional, up to 200 characters (e.g. a UUID): a retry with the same key returns the first save instead of a duplicate."

removedInput schema / properties / importance / description

Removed value: -"0.0 (routine) to 1.0 (critical), default 0.5. A floor: classification may raise it."

removedInput schema / properties / kind / description
```
Removed value: -"Optional type of memory."
```

removedInput schema / properties / project / description

Removed value: -"Project to file it under: id, slug, name or alias of a project you belong to. Unknown ones are rejected."

removedInput schema / properties / run_id / description
```
Removed value: -"Your run id."
```

removedInput schema / properties / scope / description

Removed value: -"The widest audience: 'shared' (= 'organization'), 'personal' (= 'private'), 'team' or 'project' (personal if the group cannot be resolved). Omitted: the given team or project, else the organization's default. AI checks may narrow it."

removedInput schema / properties / supersedes / description
```
Removed value: -"Id of a memory this one replaces."
```

removedInput schema / properties / team / description

Removed value: -"Team to file it under: id, slug, name or alias of a team you belong to. Unknown ones are rejected."

removedInput schema / properties / valid_until / description

Removed value: -"ISO date/datetime it stops applying (future, within 5 years)."

Changed1 schema field changedNov 8, 2026

changedInput schema / properties / scope / description

Previous value: -"Who may read it: 'shared' (= 'organization'), 'personal' (= 'private'), 'team' or 'project' ('team'/'project' fall back to personal when the group cannot be resolved). Omit it to follow the given team or project, else the organization's default audience."New value: +"The widest audience: 'shared' (= 'organization'), 'personal' (= 'private'), 'team' or 'project' (personal if the group cannot be resolved). Omitted: the given team or project, else the organization's default. AI checks may narrow it."

First observedNov 7, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive write, so the safety profile is covered. The description adds genuinely useful lifecycle context (kept until 2027-01-07) but discloses nothing about write behavior itself beyond asserting parity with save_memory. That delegation is reasonable for an alias but leaves behavior dependent on another tool's documentation.

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?

A single front-loaded sentence that identifies the alias, the canonical replacement, and the deprecation window with no wasted wording. Nothing to trim.

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

Completeness3/5

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

For an 11-parameter write tool with an output schema and 0% parameter documentation, the description is thin — it relies entirely on the agent also reading save_memory's definition. That works when both tools are in context, but the deprecation notice is otherwise complete for an alias.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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

Schema description coverage is 0% across 11 parameters, and the description only says 'same arguments and results' without explaining content, kind, scope, importance, supersedes, valid_until, or idempotency_key. An agent that encounters this tool in isolation learns nothing about what any parameter means or which combinations are valid.

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 states a specific identity (a deprecated alias) and names the canonical tool it maps to, so an agent can distinguish it from save_memory and every other sibling immediately. It also gives the retirement date, which is scope information no other field carries.

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?

The phrase 'Old name for `save_memory`' plus the removal date makes the intended routing clear: prefer save_memory for new calls. It stops short of an explicit imperative ('do not call this; call save_memory instead'), so the preference is strongly implied rather than stated.

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?