noticed

memory_save

Idempotent

Save a durable fact/preference/decision/commitment to long-term memory. Deduplicates against existing memories. Pass person to attach the memory to a specific contact's record in addition to the global store. For content about ONE person, prefer add_note (the user asked you to remember it) or add_memory (you worked it out yourself).

Input Schema

Name	Required	Description
`person`	No	Name or identifier of a specific person in your network this memory is about. When set, the memory is attached to that person's PRM record in addition to the global memory store.
`content`	Yes	The memory to save.
`category`	No	Defaults to 'fact'.
`confidence`	No	0-1 confidence (default 0.9).

Output Schema

Name	Required	Description
`ok`	Yes	Whether noticed completed the operation.
`data`	No	The operation result when ok is true.
`error`	No	A human-readable error when ok is false.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 22, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "description": "The operation result when ok is true.",
+      "properties": {
+        "action": {
+          "type": "string"
+        },
+        "prmMemoryId": {
+          "type": "string"
+        },
+        "stored": {
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "stored",
+        "action"
+      ],
+      "type": "object"
+    },
+    "error": {
+      "description": "A human-readable error when ok is false.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether noticed completed the operation.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedAug 22, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing deduplication against existing memories and the fact that `person` writes to a contact record in addition to the global store. It stops short of saying what dedup does on a hit (merge vs. skip) or what the response contains, though an output schema exists.

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?

Three sentences, each earning its place: purpose, dedup behavior, parameter effect, then the sibling routing rule. The differentiator (global store vs. person-scoped alternatives) is front-loaded with zero filler.

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?

Rich annotations, 100% schema coverage, and an output schema mean the description needn't explain return values or parameter formats. What remains — purpose, dedup, dual-write, and sibling routing — is fully addressed for a low-complexity, 4-parameter write tool.

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 each parameter already carries its own description, including the person-attachment semantics. The description restates the `person` dual-write behavior but adds nothing about `category` enumeration or `confidence` scaling beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Save a durable fact/preference/decision/commitment to long-term memory') and immediately narrows scope with 'Deduplicates against existing memories' and the dual-write behavior of `person`. An agent can tell it apart from add_note/add_memory 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?

Explicitly routes the agent away from this tool when the content concerns ONE person, naming both alternatives and the condition that selects each ('the user asked you to remember it' → add_note; 'you worked it out yourself' → add_memory). This is a genuine when/when-not rule, not implied usage.

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

All noticed 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?