Datacron

Overview Schema Source Related Servers Discussions Admin

Create memory note

create_note_ai

Capture durable facts, decisions, and user preferences as typed Markdown notes; record rejected options to prevent future agents from proposing them again.

Instructions

Call this proactively when a durable fact, confirmed decision, or user preference emerges in conversation - do not wait to be asked. Skip speculation and one-off chatter. Write a new typed _memory Markdown note. Use rejected entries in 'option -- reason' format to record discarded options so a future agent does not propose them again. This is a write operation: it is confined to DATACRON_WRITE_PATHS, never overwrites existing files, writes a durable operation record, and relies on the MCP client's tool approval for human-in-the-loop review.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`body`	Yes
`tags`	Yes
`title`	Yes
`origin`	Yes
`rejected`	No
`rel_path`	Yes
`confidence`	Yes
`request_id`	No
`supersedes`	No
`last_verified`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`created`	No
`indexed`	Yes
`rel_path`	No
`replayed`	No
`committed`	No
`content_hash`	Yes
`operation_id`	No
`organization`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.16Oct 1, 2026

addedOutput schema / properties / organization

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Organization"
+}

Changed1 schema field changedv0.1.13Sep 23, 2026

removedInput schema / properties / expected_hash

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Expected Hash"
-}

Changed9 schema fields changedv0.1.5Sep 5, 2026

addedInput schema / properties / request_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Request Id"
+}

addedOutput schema / properties / committed

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Committed"
+}

removedOutput schema / properties / created / $ref
```
Removed value: -"#/$defs/CreatedNoteOutput"
```

addedOutput schema / properties / created / anyOf

Added value: +[
+  {
+    "$ref": "#/$defs/CreatedNoteOutput"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / created / default
```
Added value: +null
```

addedOutput schema / properties / operation_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Operation Id"
+}

addedOutput schema / properties / rel_path

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Rel Path"
+}

addedOutput schema / properties / replayed

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Replayed"
+}

changedOutput schema / required

Previous value: -[
-  "created",
-  "content_hash",
-  "indexed"
-]New value: +[
+  "content_hash",
+  "indexed"
+]

First observedv0.1.0Jul 31, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only give the coarse profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), while the description adds genuinely new behavioral facts: writes are confined to DATACRON_WRITE_PATHS, existing files are never overwritten, a durable operation record is written, and human review happens through the MCP client's tool approval. That is exactly the extra context annotations cannot carry.

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 trigger condition before the mechanics, and every sentence carries information (trigger, exclusions, note format, rejected-option convention, write semantics). It is dense rather than padded, though the long middle sentence packs several distinct ideas together.

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

Completeness3/5

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 not be described, and the behavioral side is well covered. However, for a 10-parameter tool with 0% schema description coverage, the description leaves most parameter semantics undocumented, which is a real gap even if an agent could guess from names.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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

Schema description coverage is 0% across 10 parameters, so the description carries the full load, yet it only documents one field ('rejected' entries in 'option -- reason' format). Semantics for rel_path, origin, confidence, supersedes, last_verified, request_id and tags are left entirely to field names and enums.

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 ('Write a new typed _memory Markdown note') and scopes it tightly to durable facts, decisions and preferences, which separates it from siblings like append_journal or patch_note_section. An agent can identify the operation without inspecting 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when ('when a durable fact, confirmed decision, or user preference emerges - do not wait to be asked') and when-not ('Skip speculation and one-off chatter') conditions, plus a special sub-case for recording discarded options via 'rejected'. No sibling is named as an alternative, but the selection criteria are otherwise fully specified.

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