AI Team OS

by CronusL-1141

Overview Schema Source Related Servers Discussions Admin

Python

Local

task_create

Create a new task in a project (not bound to a team).

Instructions

Create a new task in a project (not bound to a team).

Project-level tasks are attached directly to the project and visible on the project task wall. Suitable for planning-phase tasks not yet assigned to a team.

Input Schema

Name	Required	Description	Default
`tags`	No	Tag list
`title`	Yes	Task title
`fields`	No	"all" (default, compatible) / "compact" write receipt	all
`horizon`	No	Time horizon, one of "short" / "mid" / "long"	mid
`priority`	No	Priority, one of "critical" / "high" / "medium" / "low"	medium
`parent_id`	No	Open top-level parent task in the same project (optional)
`task_type`	No	Ignored; accepted only so existing callers keep working. For orchestration use a CC Workflow (ultracode); its runs are tracked by workflow_list / workflow_get.
`auto_start`	No	Request running status; incomplete dependencies/waiting return blocked, without dispatch
`depends_on`	No	Same-project dependency IDs (optional)
`project_id`	No	Project ID (optional, auto-uses active project if empty)
`waiting_on`	No	Wait object with kind=user/agent, target_id and reason
`assigned_to`	No	Agent ID/name; assignment does not dispatch it
`description`	No	Task description
`status_note`	No	Current status explanation

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv1.15.2Oct 14, 2026

addedInput schema / properties / assigned_to

Added value: +{
+  "default": "",
+  "description": "Agent ID/name; assignment does not dispatch it",
+  "type": "string"
+}

changedInput schema / properties / auto_start / description

Previous value: -"If True, immediately set status to 'running' after creation"New value: +"Request running status; incomplete dependencies/waiting return blocked, without dispatch"

addedInput schema / properties / depends_on

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Same-project dependency IDs (optional)"
+}

addedInput schema / properties / fields

Added value: +{
+  "default": "all",
+  "description": "\"all\" (default, compatible) / \"compact\" write receipt",
+  "type": "string"
+}

addedInput schema / properties / parent_id

Added value: +{
+  "default": "",
+  "description": "Open top-level parent task in the same project (optional)",
+  "type": "string"
+}

addedInput schema / properties / status_note

Added value: +{
+  "default": "",
+  "description": "Current status explanation",
+  "type": "string"
+}

addedInput schema / properties / waiting_on

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Wait object with kind=user/agent, target_id and reason"
+}

Changed1 schema field changedv1.15.0Sep 30, 2026

changedInput schema / properties / task_type / description

Previous value: -"Deprecated (pipeline retired, see design doc §7) — accepted\nfor backward compatibility but no longer attaches a pipeline.\nUse CC Workflow (ultracode) for orchestration; runs are tracked\non the /workflows observability page."New value: +"Ignored; accepted only so existing callers keep working.\nFor orchestration use a CC Workflow (ultracode); its runs are\ntracked by workflow_list / workflow_get."

First observedv1.9.0Jul 14, 2026

TDQS

A3.8/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses that the task attaches directly to the project and appears on the project task wall, but it omits side effects like whether creation triggers dispatch, permission requirements, or what happens to unset optional fields. Schema descriptions cover some behavior (auto_start, assigned_to), but the description itself leaves meaningful gaps.

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?

Two short sentences, front-loaded with the core action and scoping constraint, with no redundant or filler text. The project-wall visibility sentence earns its place by clarifying the consequence of the scope choice.

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

Completeness4/5

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 no explanation, and the full-coverage schema handles parameters. The description adequately conveys purpose and scope, but for a 14-parameter mutation tool with zero annotations it could do more on behavioral consequences and alternatives.

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%, so the schema already documents all 14 parameters in detail; baseline is 3. The description adds no parameter-level meaning (e.g., project_id defaulting, parent/hierarchy rules) beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (create a task) and adds a scoping qualifier ('not bound to a team') that distinguishes it from team-assigned tasks. However, it does not name the closest siblings like task_create_batch or task_update, so differentiation is only partial.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

The description gives a clear use condition: planning-phase tasks not yet assigned to a team, and explains the project-wall visibility rationale. It provides context but no explicit exclusions or named alternatives for when a different creation path should be used.

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

Deploy Server