MemScope

Correct memory

correct_memory

Use this when a saved fact is wrong or has changed: stores new_content as a new version, keeps the history and re-classifies it; the result's visible_to says who can read it now. To change who can read a memory, use change_scope or change_sensitivity instead.

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": {
      "memory_id": "<memory_id>",
      "new_content": "<new_content>",
      "reason": "<reason>"
    },
    "name": "correct_memory"
  }
}

Input Schema

Name	Required	Description
`kind`	No	Type of memory; 'none' clears it.
`agent`	No	Your agent label.
`reason`	Yes	Why, for the audit; ask the person if unsure.
`run_id`	No	Your run id.
`memory_id`	Yes	Memory id ('mem_' prefix optional).
`new_content`	Yes	The corrected text: one self-contained fact, up to 8000 characters.
`valid_until`	No	As in remember; 'none' clears it.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 8, 2026

removedInput schema / properties / reason / anyOf

Removed value: -[
-  {
-    "maxLength": 500,
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / reason / default
```
Removed value: -null
```

changedInput schema / properties / reason / description

Previous value: -"Why, kept in the audit trail. Up to 500 characters."New value: +"Why, for the audit; ask the person if unsure."

addedInput schema / properties / reason / maxLength
```
Added value: +500
```
addedInput schema / properties / reason / type
```
Added value: +"string"
```

changedInput schema / required

Previous value: -[
-  "memory_id",
-  "new_content"
-]New value: +[
+  "memory_id",
+  "new_content",
+  "reason"
+]

First observedNov 7, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses that history is preserved, that the content is stored as a new version rather than overwritten, that it is re-classified, and that visibility is reported via result `visible_to`. That is substantive behavioral context; failure modes (nonexistent memory_id, repeated corrections stacking versions) are not covered, which keeps it below a 5.

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: the first front-loads the trigger and the core effect, the second handles the alternative. No restated title, no filler, and the exclusion is placed after the primary behavior where it belongs.

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

Completeness4/5

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

For a mutation tool with a rich 7-parameter schema, full schema coverage, an output schema, and annotations, the description supplies the essential missing pieces: versioning semantics, history preservation, and result visibility. The absence of guidance on how this differs from supersede_memory is the main residual gap.

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% and an output schema exists, so the schema already documents memory_id, new_content, kind, reason, and valid_until. The description adds only that new_content becomes a new version and that classification is redone, which is useful framing but does not extend the meaning of individual parameters. 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?

States a specific verb and resource ('stores `new_content` as a new version, keeps the history and re-classifies it') plus the triggering condition ('a saved fact is wrong or has changed'). It also names the siblings it is not (change_scope, change_sensitivity), so an agent can distinguish it from nearby tools 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 gives both when to use it (facts that are wrong or changed) and when to use something else instead (scope/visibility changes go to change_scope or change_sensitivity). The only gap is that the closely related supersede_memory sibling is never contrasted, but the routing guidance is otherwise direct.

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?