Skip to main content
Glama

Create a task

create_task

Turn a finding into first-class work: creates a task-type concept with taskStatus=open and the given relations — part_of a domain and/or an epic, realizes stories/features, governed_by specs — plus codeAreas pointing at where the work lands. Use when you discover work that isn't reflected in the codebase yet (a gap, a needed fix, a follow-up). The task then shows up in list_tasks / take_task and on the Kanban board.

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": {
      "title": "<title>",
      "body": "<body>"
    },
    "name": "create_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesMarkdown description of the work. [[wiki-links]] become edges.
epicNoEpic concept id this task is part_of (the overarching body of work it belongs to).
tagsNoTags, e.g. a priority tag like "high" or an area tag.
titleYesHuman-readable task title (required, non-empty).
domainNoDomain concept id this task is part_of.
realizesNoStory/feature concept ids this task realizes (creates `realizes` edges).
codeAreasNoRough codebase paths/globs where the work lands.
governedByNoSpec concept ids that govern this task (creates `governed_by` edges).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / epic
      Added value: +{
      +  "description": "Epic concept id this task is part_of (the overarching body of work it belongs to).",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare write/non-destructive/non-open-world, so the description carries the real burden and does add value: it discloses that a concept is created with taskStatus=open, that body wiki-links become edges, and that realizes/governedBy produce typed relations. It does not cover idempotency or duplicate-title behavior, nor what is returned (id? URL?), which matters for a creation tool.

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?

Two sentences, front-loaded with the core action and the resulting state, then the usage trigger. The middle enumeration of relations is dense and partly redundant with the schema, but it reads as a single purposeful clause rather than padding.

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?

For an 8-parameter creation tool with full schema descriptions and no output schema, the description covers what is created, what defaults apply, what side-effect edges appear, and where the result surfaces. The remaining gap is post-call behavior — the returned identifier and how to subsequently reference or take the task — which an agent would need for a follow-up call.

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% and the schema already spells out concept ids and edge creation, so most of the description's relation listing is restatement. The one genuine addition is the 'part_of a domain and/or an epic' phrasing, clarifying that either or both of those relation params may be supplied, but that is a marginal gain over the baseline.

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?

Opens with a specific verb-plus-resource framing ('Turn a finding into first-class work: creates a `task`-type concept') and pins down the created state (taskStatus=open) plus the edge types that will be written. An agent can distinguish this from upsert_concept, create_vault, or link_concepts without inspecting the schema.

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?

Gives a concrete trigger condition — 'Use when you discover work that isn't reflected in the codebase yet (a gap, a needed fix, a follow-up)' — and names the downstream tools where the result reappears (list_tasks / take_task, Kanban board). It stops short of stating when not to use it, e.g. that arbitrary non-task concepts belong in upsert_concept or that relation wiring on existing concepts belongs in link_concepts.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources