Mnemosyne OS

Overview Schema Source Related Servers Discussions Admin

mnemosyne_todo_update

Destructive

Apply changes to the user's to-do backlog in one save: edit, complete, move, archive, or delete tasks and attach files, with per-operation results.

Instructions

Change the user's To-do backlog: edit a task, tick it off, move it to another list, or take it out. Every operation names a task by the id from mnemosyne_todo_list, so call that first. Removing a task archives it by default, and it can be restored. Pass permanent: true only when the user asked for it to be deleted outright. The whole batch is applied in order as one save, and each operation reports its own outcome, so a stale id does not sink the ones around it. Works with the app closed on a dev install (the headless daemon reads the file); an npm install has no daemon and needs the app running. Scope todo:write.

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": {
      "ops": "<ops>"
    },
    "name": "mnemosyne_todo_update"
  }
}

Input Schema

Name	Required	Description	Default
`ops`	Yes	The changes, applied in order. Up to 100 per call.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv2.0.0-infinityNov 1, 2026

addedInput schema / properties / ops / items / properties / dropped

Added value: +{
+  "default": false,
+  "description": "remove: archive it as « not planned » rather than as tidied away.",
+  "type": "boolean"
+}

addedInput schema / properties / ops / items / properties / kind

Added value: +{
+  "description": "edit: \"note\" turns a task into context (not ticked, counted nowhere); \"task\" turns it back.",
+  "enum": [
+    "note",
+    "task"
+  ],
+  "type": "string"
+}

addedInput schema / properties / ops / items / properties / label

Added value: +{
+  "description": "attach: a name to show instead of the file name.",
+  "type": "string"
+}

changedInput schema / properties / ops / items / properties / op / description

Previous value: -"edit = rewrite text/description/colour/step/due date. complete = tick or un-tick. move = send to another list. remove = archive it, or delete it with permanent: true."New value: +"edit = rewrite text/description/colour/step/due date/status/priority, or turn it into a note. complete = tick or un-tick (a note cannot be ticked). move = send to another list. remove = archive it (dropped: true marks it « not planned »), or delete it with permanent: true. attach = attach a file or folder by absolute path. detach = take an attachment off by its path."

changedInput schema / properties / ops / items / properties / op / enum

Previous value: -[
-  "edit",
-  "complete",
-  "move",
-  "remove"
-]New value: +[
+  "edit",
+  "complete",
+  "move",
+  "remove",
+  "attach",
+  "detach"
+]

addedInput schema / properties / ops / items / properties / path

Added value: +{
+  "description": "attach / detach: the ABSOLUTE path of the file or folder. Nothing is read: only the path is stored.",
+  "type": "string"
+}

addedInput schema / properties / ops / items / properties / priority

Added value: +{
+  "description": "edit: high or low. null is normal.",
+  "enum": [
+    "high",
+    "low",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedInput schema / properties / ops / items / properties / status

Added value: +{
+  "description": "edit: where its work stands. null puts it back to « to do ».",
+  "enum": [
+    "doing",
+    "waiting",
+    "someday",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedInput schema / properties / ops / items / properties / task / description

Previous value: -"The task id, exactly as mnemosyne_todo_list printed it in brackets."New value: +"The task id, exactly as mnemosyne_todo_list printed it in brackets, or its number (#42)."

First observedv1.10.0Sep 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the destructiveHint annotation, it discloses that removal archives by default and is restorable, that the batch is applied in order as one save, and that each operation reports its own outcome so a stale id doesn't sink its neighbors. It also discloses the auth scope (todo:write) and the daemon/app-running dependency — meaningful behavioral context not present in structured fields.

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 purpose and the operation list, then prerequisites, then the destructive caveat, then environment notes. Dense and mostly waste-free, though the daemon/install sentence is somewhat incidental and could be trimmed for a mutation tool.

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 batch mutation tool with no output schema, it covers what an agent needs: id sourcing, ordering and partial-failure semantics, recoverability of removals, the deletion escape hatch, auth scope, and runtime requirements. Little is left to inference.

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% and nested op descriptions are already thorough, so baseline is 3. The description adds real value by clarifying that every op names a task by the id printed in brackets by mnemosyne_todo_list, and by reinforcing the permanent default semantics over the archive behavior.

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 (change) and resource (user's To-do backlog) and enumerates the operation families: edit, complete, move, remove. It also distinguishes itself from mnemosyne_todo_add and mnemosyne_todo_list by framing all operations as id-based mutations on existing tasks.

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 an explicit prerequisite ('call mnemosyne_todo_list first' to obtain ids) and an explicit exclusion rule for the destructive path: pass permanent: true only when the user asked for outright deletion. The environment caveat (headless daemon on dev installs vs. app must be running after npm install) further guides correct invocation.

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