Skip to main content
Glama

task_create

Capture durable multi-session work as a Taskwarrior task, so blockers, follow-ups, and handoffs persist beyond the current session. Deduplicates automatically and can claim the task at creation.

Instructions

Create a durable task for work that outlives this session (multi-session work, blockers, follow-ups, handoffs). Not for work you finish now. Project comes from the session folder unless job/repo is given. Returns an existing open task instead of a duplicate. claim:true claims it immediately.

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": {
      "description": "<description>"
    },
    "name": "task_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoSession folder (absolute path). Filled in by the OpenCode plugin; other clients pass the working folder.
dueNo
jobNoOverride: job (e.g. acme). Normally derived from the session folder.
gateNoOperator methodology gate 0-8.
kindNo
noteNoFirst note.
repoNoOverride: repo within the job. Normally derived from the session folder.
riskNoOperator methodology risk class.
tagsNosnake_case tags, one per item.
waitNoKeep out of NEXT until this date.
claimNo
dedupeNoDefault true.
dependsNoIds of tasks that must finish first. On update this replaces the list ([] clears it).
projectNoOverride: exact project job.repo.
priorityNoH = important and near-term, M = soon, L = backlog.
repo_pathNoCanonical folder being changed. Defaults to the session folder (not operator lanes).
scheduledNo
waiting_onNoOwner-dependent: who must act (e.g. "owner approval"). Kept out of NEXT until cleared with "".
descriptionYes
all_projectsNoCross-project view. Only for explicit global review.
context_summaryNoHandoff-quality context: what, why, where it stands.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and discloses meaningful behavior: deduplication ('Returns an existing open task instead of a duplicate'), project derivation from the session folder with job/repo overrides, and immediate claiming via claim:true. It does not say what happens to conflicting fields on a dedupe hit or what identifier is returned.

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 and exclusion, then key behaviors, in five short clauses with no filler. The telegraphic 'claim:true claims it immediately' is slightly terse but still parseable and earns its space.

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 a 21-parameter create tool with no output schema, it covers the selection decision, the dedupe return behavior, and project-derivation logic, which are the non-obvious parts. What is missing is a fuller statement of the return value and whether duplicates merge the supplied note/context_summary.

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 76%, and the description adds genuine meaning on top of it, particularly the interaction between cwd, project, job, and repo ('Project comes from the session folder unless job/repo is given') and the effect of claim:true. The remaining parameters (depends, waiting_on, wait, gate, risk) are left to the schema.

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?

Opens with a specific verb and resource ('Create a durable task') and immediately scopes it to work that outlives the session, which separates it from transient work. It does not explicitly contrast with task_claim or task_update, but the verb plus the 'durable/persistent' framing makes the resource unambiguous.

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 an explicit when-not ('Not for work you finish now') and narrows to multi-session work, blockers, follow-ups, and handoffs. It omits naming alternatives such as task_update for existing tasks, so the boundary with siblings is implied rather than spelled out.

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