MemScope

Review memory

review_memory

Use this when resolving a memory from review_queue: 'approve' clears the flag, 'reroute' shares it with a team, project or the organization, 'tighten' sets a stricter sensitivity or keeps it to its author. A wider or different audience or a lower sensitivity follows the confirm_widen rule.

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>",
      "action": "<action>",
      "reason": "<reason>"
    },
    "name": "review_memory"
  }
}

Input Schema

Name	Required	Description
`team`	No	For a team reroute: id, slug, name or alias of a team the person belongs to.
`agent`	No	Your agent label.
`scope`	No	For 'reroute': 'team' (needs `team`), 'project' (needs `project`) or 'organization'.
`action`	Yes	'approve' clears the flag; 'reroute' shares it (give `scope`); 'tighten' sets a stricter `sensitivity`, or keeps it to its author when `sensitivity` is omitted.
`reason`	Yes	Why, for the audit; ask the person if unsure.
`run_id`	No	Your run id.
`project`	No	For a project reroute: id, slug, name or alias of a project the person belongs to.
`memory_id`	Yes	Memory id ('mem_' prefix optional).
`sensitivity`	No	For 'tighten': a stricter sensitivity to set; lowering it follows the confirm_widen rule. Omit it to keep the memory to its author.
`confirm_human`	No	True only if the person approved clearing the flag on a memory you saved.
`confirm_widen`	No	Set true only after the person agreed; a widening change without it gets confirm_required.

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",
-  "action"
-]New value: +[
+  "memory_id",
+  "action",
+  "reason"
+]

First observedNov 7, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Goes beyond the annotations by explaining the per-action effects and, importantly, the failure mode: a widening change without `confirm_widen` returns 'confirm_required'. It also flags that `reason` feeds an audit trail. It stops short of saying what happens to the memory's visibility after approval or why the operation is non-idempotent, so not 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger condition, then the action semantics, then the guardrail rule — a sensible order with little waste. The final sentence about the confirm_widen rule is slightly compressed and takes a second read, but nothing is redundant.

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 an 11-parameter mutation tool with an output schema (so return values need no explanation), the description covers the action space and the human-consent guardrails adequately. It leaves open the post-approval visibility outcome and how it relates to the change_scope/change_sensitivity siblings, which would be useful for a tool this configurable.

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 documents every parameter including the action/scope/sensitivity enums. The description largely restates the enum semantics ('reroute' shares it, 'tighten' sets a stricter sensitivity) and adds only the confirm_widen gating rule, which is marginal value over the schema baseline.

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?

Names a specific resource and operation ('resolving a memory from `review_queue`') and enumerates the three actions with distinct effects ('approve' clears the flag, 'reroute' shares it, 'tighten' restricts it). An agent can distinguish this from siblings like change_scope and change_sensitivity without opening the schema.

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?

States the triggering condition clearly ('Use this when resolving a memory from `review_queue`') and gives the escalation rule for widening changes. It does not explicitly name change_scope or change_sensitivity as the tools to use outside the review flow, so the routing is implied rather than exhaustive.

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?