Skip to main content
Glama
Sign In
SetLuca

SetLuca

Official
by setluca
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Edit a memory

luca_memory_update
Destructive

Correct one memory: edit the fact, flag it disputed when it turns out to be wrong, restore an archived one, or make it win over a conflicting memory.

Instructions

Correct one memory: edit the fact, flag it disputed when it turns out to be wrong, restore an archived one, or make it win over a conflicting memory.

Luca operation: PATCH /api/memory/{id} Required scopes: memory:write Required OAuth scope: luca:draft; data sensitivity: full_content Requires Idempotency-Key. Provide idempotencyKey for safe retries, or the server will generate one. Use workspaceId or workspaceSlug to override the default workspace configured by environment.

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": {
      "id": "<id>"
    },
    "name": "luca_memory_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
bodyNo
workspaceIdNoOptional Luca workspace id override.
workspaceSlugNoOptional Luca workspace slug override.
idempotencyKeyNoStable key for safe retries. If omitted, the MCP server generates a unique key for this call.

Output Schema

NameRequiredDescriptionDefault
resultYes
provenanceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.4.1
    • addedInput schema / properties / body / properties / evidence / additionalProperties
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "object"
+    },
+    {
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
    • addedInput schema / properties / body / properties / metadata / additionalProperties
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "object"
+    },
+    {
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
    • changedInput schema / required
      Previous value: -[
-  "id",
-  "body"
-]New value: +[
+  "id"
+]
    • addedOutput schema / properties / result / properties / factOrigin
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
    • addedOutput schema / properties / result / properties / sourceField
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
  2. First observedv0.4.0

TDQS

A3.8/5.0
Behavior4/5

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

With destructiveHint=true and idempotentHint=false already in annotations, the description still adds meaningful context: required memory:write scope, luca:draft OAuth scope, full_content data sensitivity, and the server-side idempotency-key fallback. It does not mention optimistic concurrency (expectedUpdatedAt) or whether omitted body fields are cleared on a PATCH, which matters for a destructive edit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The opening sentence is dense and front-loaded, which is good. The trailing block, however, restates what the schema already documents for idempotencyKey and workspaceId/workspaceSlug, spending space on duplicated semantics instead of the undocumented body fields.

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?

An output schema exists, so return values need no explanation, and the description covers auth scopes, sensitivity, idempotency and workspace override for a destructive single-record PATCH. The remaining gap is partial-update semantics and the expectedUpdatedAt concurrency precondition, both of which an agent would want before calling.

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 60%, so the schema carries part of the burden, and the description maps its four modes onto content/disputed/restore/preferred. But the more consequential nested parameters — expectedUpdatedAt (concurrency guard), confidence, trustLevel, evidence, sourceRefId — get no mention anywhere in the description, leaving the 40% gap only partially filled.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource (correct/edit a memory) and enumerates the four distinct modes: edit the fact, flag disputed, restore an archived one, preferred over a conflicting memory. That maps closely to the body fields (content, disputed, restore, preferred). It does not, however, distinguish itself from the sibling luca_memory_set_archived, which overlaps with the 'restore' mode.

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?

Each mode is paired with the condition that selects it ('flag it disputed when it turns out to be wrong', 'restore an archived one', 'make it win over a conflicting memory'), which is real when-to-use guidance rather than a restatement of the name. It stops short of naming an alternative tool or stating when NOT to use this one versus luca_memory_set_archived.

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

Deploy Server

Other Tools