Skip to main content
Glama

add_task

Add a task with automatic routing to the best workflow and assignment by role. Override with explicit workflow, assignee, or priority as needed.

Instructions

Add a task — autonomous by default. Just pass a title and the server will (a) auto-ROUTE the task to the workflow it best fits (matched from the task text against workflow names/descriptions), falling back to the workspace's "General" workflow when no workflow clearly relates, and (b) auto-ASSIGN it to the right team member(s) by role/default. Every task belongs to a workflow — there is no workspace-level task. The caller does NOT need to choose a workflow or assignee. Provide an explicit workflowId/workflowName and/or assigneeIds ONLY to override that decision (the user has already decided) — explicit values are used verbatim and skip auto-routing/auto-assignment for whatever was specified. Set autoRoute:false to skip AI routing and place the task directly in the "General" workflow. Tasks are stored as DB tasks under the chosen workflow by default; only legacy workflows that still have a file-backed project library store the task as a phase file tagged "task".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTask title — short, actionable description.
dueDateNoOptional due date — a calendar date "YYYY-MM-DD" or a full ISO 8601 datetime. Once set, the task surfaces in due-soon / overdue nudges.
priorityNoTask priority — high, medium, or low. AI agents should set this based on urgency and importance.
autoRouteNoWhen true (the default) and no workflow is given, the task is auto-routed to the best-fit workflow, falling back to the workspace's "General" workflow if none relates. Set false to skip AI routing and place it directly in the "General" workflow. Ignored when an explicit workflowId/workflowName is provided.
assignedToNoUser ID to assign the task to. Overrides the workflow default assignee when provided.
autoAssignNoWhen true (the default) and no explicit assignee is given, the task is auto-assigned to the team member(s) whose job role best fits it. Set false to leave it unassigned.
workflowIdNoExact workflow ID. Use this when you already know the ID.
assigneeIdsNoUser IDs to assign this task to as a SHARED task that any one of them can complete (max 5). Only assign multiple people when the task genuinely needs more than one owner — do not blanket-assign. Prefer one assignee unless the task spans several roles.
descriptionNoOptional longer description or context for the task.
phaseFileIdNoLegacy: phase file ID to link this task to, for workflows still using a file-backed project library. New workflows use DB-backed phases (add_phase) and do not need this.
workspaceIdNoWorkspace ID. Defaults to your configured workspace.
workflowNameNoWorkflow name or partial name. Used to look up the workflow when you don't know the ID. If multiple workflows match, candidates are returned so the user can pick.
Behavior5/5

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

Without annotations, the description fully discloses behavioral traits: auto-routing logic, fallback to General workflow, auto-assignment by role, override semantics, storage differences between legacy and new workflows. No contradictory annotations exist.

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?

The description is a single dense paragraph that is information-rich without being overly verbose. Every sentence contributes value. However, it could be more scannable with bullet points or shorter sentences.

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?

Given 12 parameters, no output schema, and numerous siblings, the description covers the essential aspects: behavior, defaults, overrides, and storage nuances. It lacks mention of return value or error/validation behavior, but overall it's thorough for a complex tool.

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%, but the description adds significant context beyond the schema descriptions, such as assigneeIds max 5 and the shared task concept, autoRule interaction with explicit workflowId, and legacy phaseFileId. The description enhances understanding meaningfully.

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?

The description clearly states 'Add a task — autonomous by default' and explains the core functionality of auto-routing and auto-assignment. It distinguishes this create operation from siblings like update_task and break_down_task by focusing on task creation with intelligent defaults.

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 explicit guidance on when to use auto-features and when to override them with explicit workflowId/assigneeIds or autoRoute:false. It could be more explicit about when not to use this tool in favor of alternatives, but the context is clear enough.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/contextium-io/contextium-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server