Skip to main content
Glama

karea_create_subtask

Create a subtask under an existing parent task using its visual ID, name, or UUID. Supports deadlines, tags, priority, and session linking.

Instructions

Create a subtask under a parent task. Accepts the parent by visual ID (e.g. KPL77), name, or UUID. Supports the same params as karea_create_task.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slaNoDeadline: 2d, 5h, tomorrow, monday
tagsNoTags to attach. STRICT: only pass tags that already exist in this project (verify with karea_view_task or the project list). Do NOT invent new tags unless the user explicitly asked for one — a typo or a paraphrase spawns duplicate tags. When unsure, omit and ask the user.
titleYesSubtask title
parentYesParent task name, visual ID (KPL77, C1), or UUID
sourceNoWhere this subtask came from
categoryNoCategory name (defaults to the parent's category if omitted)
markdownNoLong-form markdown content — investigation findings, technical/functional docs, solution design, root cause analysis.
priorityNoPriority 1-5 (1=critical)
toolTypeNoOptional: your AI provider ("claude-code" / "opencode" / "codex" / "cursor" / "aider" / "other"). Required when aiSessionId is supplied.
projectIdNoProject name or ID (needed if parent is a visual ID)
aiSessionIdNoOptional: your current AI CLI session ID. When paired with toolType, atomically links this session to the affected task (equivalent to calling karea_link_session, but saves the round-trip). For Claude Code use the id from `claude --resume`.
descriptionNoSubtask description. Rendered as Markdown - use `**bold**`, lists, `code`, links, etc. Keep it short.
jiraIssueKeyNoJIRA issue key to link (e.g. PROJ-123). Issue must exist in JIRA.
sessionLabelNoOptional short label for the linked session (e.g. "Feature draft").
closingRequisitesNoRequirements that must be met before closing. Keep each one short and concrete - 1 short sentence, ideally under ~120 chars (e.g. "Tests pass in CI", "PR approved"). Do NOT write paragraphs.
Behavior2/5

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. It only states creation of a subtask but does not explain side effects like session linking (via aiSessionId), required permissions, or what happens on failure.

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?

The description is two sentences long, front-loading the core purpose and key parent identification detail. Every sentence adds value without redundancy.

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

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite 15 parameters and no output schema or annotations, the description provides minimal behavioral context. It does not explain return values, failure modes, or the effect of optional parameters like aiSessionId. The schema descriptions are thorough but the tool definition as a whole lacks completeness for an agent to fully understand behavior.

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 coverage is 100% with detailed parameter descriptions. The description adds context for the 'parent' parameter (accepted formats) and reference to karea_create_task parameters, but these additions are minor compared to the rich schema descriptions.

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 the verb 'Create' and resource 'subtask under a parent task', and specifies how to identify the parent (visual ID, name, or UUID). It distinguishes from sibling karea_create_task by indicating it creates a subtask and supports the same parameters.

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

Usage Guidelines3/5

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

The description implies usage for creating subtasks but does not explicitly state when to use this tool versus alternatives like karea_create_task. It provides no when-not guidance or prerequisites.

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/starecz/karea-mcp'

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