Skip to main content
Glama
Mnemosyne-OS

Mnemosyne OS

by Mnemosyne-OS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mnemosyne_todo_add

Add tasks to the user's To-do backlog or canvas widget in order, optionally under named steps and a chosen list; create one when needed after a conversation settles what to do.

Instructions

Put tasks into the user's To-do backlog, the To-do widget on their canvas, in order and optionally under named steps. Use it when a conversation has settled what to do. Name the destination list in "list": call once without it to get the existing lists back on a LIST_NOT_FOUND answer, or pass create_list: true to make a new one. Always name a list. The app routes the write through the widget's own store, so what you file is what the user sees. 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. To read the backlog back or change what is in it, see mnemosyne_todo_list, mnemosyne_todo_update and mnemosyne_todo_categories.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
listNoDisplayed name of the destination list, case-insensitive: "Today", "WIP", or a list the user created. Omitted, it goes to the first original list. An unknown name with create_list false is refused, and the answer gives the names that exist.
colorNoHex colour (#rrggbb) for a list being created. Optional; the host picks the next swatch otherwise.
tasksYesThe tasks, in execution order. Each item is a string, or {"text": string, "group": string, "description": string} where group is the STEP the task belongs to (e.g. "Step 1 · Mockup"); tasks with the same group are shown under one header in the list. One concrete, actionable line each, 300 characters max; longer detail goes in description (4000 max). A longer text is filed shortened and the answer says so.
create_listNoCreate the list named in "list" when it does not exist. Default false, so an agent does not invent lists in someone's backlog without saying so.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.7.0-infinity
    • changedInput schema / properties / tasks / description
      Previous value: -"The tasks, in execution order. Each item is a string, or {\"text\": string, \"group\": string} where group is the STEP the task belongs to (e.g. \"Step 1 · Mockup\"); tasks with the same group are shown under one header in the list. One concrete, actionable line each; 300 characters max."New value: +"The tasks, in execution order. Each item is a string, or {\"text\": string, \"group\": string, \"description\": string} where group is the STEP the task belongs to (e.g. \"Step 1 · Mockup\"); tasks with the same group are shown under one header in the list. One concrete, actionable line each, 300 characters max; longer detail goes in description (4000 max). A longer text is filed shortened and the answer says so."
    • changedInput schema / properties / tasks / items / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "properties": {
-      "group": {
-        "type": "string"
-      },
-      "text": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "text"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "properties": {
+      "description": {
+        "type": "string"
+      },
+      "group": {
+        "type": "string"
+      },
+      "text": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "text"
+    ],
+    "type": "object"
+  }
+]
  2. Changed2 schema fields changedv1.6.0-infinity
    • changedInput schema / properties / create_list / description
      Previous value: -"Create the list named in \"list\" when it does not exist. Default false: an agent must not invent lists in someone's backlog without saying so."New value: +"Create the list named in \"list\" when it does not exist. Default false, so an agent does not invent lists in someone's backlog without saying so."
    • changedInput schema / properties / list / description
      Previous value: -"Displayed name of the destination list (case-insensitive), e.g. \"En cours\", \"WIP\", or a list the human created. Omitted = the first original list. Unknown name + create_list false = refused with the names that exist."New value: +"Displayed name of the destination list, case-insensitive: \"Today\", \"WIP\", or a list the user created. Omitted, it goes to the first original list. An unknown name with create_list false is refused, and the answer gives the names that exist."
  3. First observedv1.10.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only state readOnlyHint=false and destructiveHint=false; the description adds substantial context beyond that: the write is routed through the widget's own store so the user sees exactly what is filed, dev-install headless daemon behavior vs npm installs needing the app running, and the 300/4000 character truncation outcome with an explicit answer note.

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 then the list-naming rule, with the operational caveats (daemon/npm, store routing) placed after the actionable instruction. Dense and mostly waste-free, though the install-mode sentence is somewhat tangential to invoking the 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 mutation tool with no output schema, it covers the full picture an agent needs: required tasks format, list resolution, creation semantics, truncation feedback, and environmental preconditions. Nothing material 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 the baseline is 3, but the description adds real meaning: the case-insensitive fallback to the first original list, why create_list defaults to false ('so an agent does not invent lists in someone's backlog without saying so'), and that group maps to a displayed step header. Only the color parameter is left entirely to the schema.

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+resource ('Put tasks into the user's To-do backlog, the To-do widget on their canvas') with scope beyond the name, including ordering and optional steps. It distinguishes itself from the read/update siblings it names explicitly.

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 the trigger condition ('Use it when a conversation has settled what to do'), a concrete list-naming procedure including the LIST_NOT_FOUND discovery call and create_list: true, and routes the agent to mnemosyne_todo_list/_update/_categories for other operations. This is about as complete as guidance gets.

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