Renor

Save (or correct) a memory

save_memory

DestructiveIdempotent

Structured save only: one fact as subject, predicate and object, e.g. save_memory({"subject": "Fjord", "predicate": "database", "object": "SQLite"}). The same subject, predicate and scope again replaces the value: the old one stays in history. A save by a different agent than the one that saved the current value still replaces it, but the replaced value is then shown in reads as a CONFLICT line (its writer and date) until that agent saves this subject and predicate again. The writer is the connection's authenticated agent name, never the source you pass. The receipt says store, supersede or nochange, and may list possibleDuplicates (see remember). All three fields are required and no sentence of yours is kept: to save plain words, or a fact with your words, call remember.

Input Schema

Name	Required	Description
`cites`	No	Optional, never required. What this save builds on: the notePath (or memory id) of a note a read returned, or the subject of a fact it returned. Lets Renor tell that reading helped.
`scope`	No	"global" (default) or project:<slug>, e.g. project:atlas.
`object`	No	The value, e.g. "Memory Company"
`source`	No	Name of the app or agent saving this, for example claude-code. Leave it out to use the connecting client. Never a file path or document name.
`subject`	No	Who/what the fact is about, e.g. "user"
`predicate`	No	The relationship, e.g. "works_at"

Output Schema

Name	Required	Description	Default
`ok`	Yes
`action`	Yes
`closed`	No
`ledger`	Yes
`created`	No
`eventId`	Yes
`subject`	Yes
`predicate`	Yes
`alsoClosed`	No
`possibleDuplicates`	No
`possibleDuplicatesTotal`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "action": {
+      "enum": [
+        "store",
+        "supersede",
+        "nochange"
+      ],
+      "type": "string"
+    },
+    "alsoClosed": {
+      "anyOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "factId": {
+              "type": "number"
+            },
+            "object": {
+              "type": "string"
+            },
+            "validTo": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "factId",
+            "object",
+            "validTo"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "closed": {
+      "anyOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "factId": {
+              "type": "number"
+            },
+            "object": {
+              "type": "string"
+            },
+            "validTo": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "factId",
+            "object",
+            "validTo"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "created": {
+      "anyOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "factId": {
+              "type": [
+                "number",
+                "null"
+              ]
+            },
+            "object": {
+              "type": "string"
+            },
+            "validFrom": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "factId",
+            "object",
+            "validFrom"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "eventId": {
+      "type": "string"
+    },
+    "ledger": {
+      "type": "string"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "possibleDuplicates": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "object": {
+            "type": "string"
+          },
+          "scope": {
+            "type": "string"
+          },
+          "source": {
+            "type": "string"
+          },
+          "subject": {
+            "type": "string"
+          },
+          "untrusted": {
+            "const": true,
+            "type": "boolean"
+          },
+          "validFrom": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "subject",
+          "object",
+          "scope",
+          "validFrom"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "possibleDuplicatesTotal": {
+      "type": "number"
+    },
+    "predicate": {
+      "type": "string"
+    },
+    "subject": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok",
+    "action",
+    "eventId",
+    "subject",
+    "predicate",
+    "ledger"
+  ],
+  "type": "object"
+}

First observedOct 17, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well beyond the annotations: explains that a repeated subject/predicate/scope supersedes while keeping history, that cross-agent writes are honored but surface as CONFLICT until the other agent re-saves, that the writer is always the authenticated connection agent (never the `source` value), and what the receipt contains. The only gap is it doesn't explain what 'destructiveHint: true' means in practice, e.g. whether history is ever purged.

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-loads the structured-only rule and the example, then layers supersede/conflict/receipt/writer semantics, ending with the routing pointer to `remember`. It is a dense single paragraph — appropriate content, but it would scan better broken into short clauses.

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 mutation with an output schema and full annotation coverage, the description supplies everything behaviorally important: key semantics, history retention, conflict state, writer identity, receipt vocabulary, and the sibling alternative. Nothing needed 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.

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: the composite key is subject+predicate+scope, and `source` is provenance only, never the recorded writer. It also states all three fields are required, which conflicts with the schema's empty `required` list — a discrepancy worth resolving but the description is doing the heavier lifting correctly.

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 ('Structured save only: one fact as subject, predicate and object') and gives a literal call example. It explicitly separates itself from the sibling tool 'remember' for free-form text, so an agent can route without opening either 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?

Explicit when-to-use ('structured save only') and when-not ('to save plain words, or a fact with your words, call remember'). It also names the condition that changes behavior — a save by a different agent than the current writer produces a CONFLICT line.

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

All Renor 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.