Skip to main content
Glama

Create a task

create_task

Create a task. A "schedule" task needs exactly one of dow, cron or every_days. To put a task in a loop, create it with task_type "loop", then call enqueue_task.

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

Input Schema

NameRequiredDescriptionDefault
dowNoDays of the week as a bitmask: Monday=1, Tuesday=2, Wednesday=4, Thursday=8, Friday=16, Saturday=32, Sunday=64. 127 = every day, 31 = weekdays. 0 = none (use with cron or every_days).
cronNoCron schedule, 5 fields; only the date fields (day of month, month, weekday) matter: minute and hour are ignored, so write them as "0 0" (e.g. "0 0 * * 1" = Mondays). Alternative to dow and every_days (one schedule system at a time). Do not use "*/N" in the day field for "every N days": it restarts each month; use every_days.
nameYesTask name.
everyNoSubtasks: armed every N runs of the parent.
end_dateNoLast day it applies, YYYY-MM-DD. null clears it.
is_activeNofalse pauses it without deleting it.
task_typeNo"schedule": due on its dow, cron or every_days days (exactly one of them). "loop": a member of a loop's queue (then use enqueue_task). "subtask": armed every "every" runs of parent_task_id.
every_daysNoStrict interval: due every N days, counted from start_date (the anchor; defaults to today in the user's time zone). A missed day does not shift the cycle. Schedule tasks/loops only, and instead of dow and cron (send dow 0 / cron null with it). null removes it.
start_dateNoFirst day it applies, YYYY-MM-DD; with every_days, the first day of the interval. null clears it.
descriptionNoLonger notes.
parent_task_idNoSubtasks: the parent task's id.
task_missed_behaviorNoSchedule tasks: what happens when a due day passes unchecked. "reschedule" keeps it armed, "drop" skips it automatically (abortions +1).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write. The description adds the mutual-exclusivity rule and the follow-up enqueue_task step, but says nothing about whether duplicate names create duplicates, what is returned (needed for the enqueue_task follow-up), or side effects of subtask creation.

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?

Three short sentences, front-loaded with the purpose and then the two most error-prone rules. Nothing is redundant, though the loop sentence is slightly clipped about whether it substitutes for create_loop.

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

Completeness3/5

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

For a 12-parameter creation tool with no output schema and rich schema text, the description covers the main configuration pitfalls but omits the result (task id) that the recommended enqueue_task follow-up requires, and does not address the subtask branch beyond what the schema says.

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?

With 100% schema coverage, the baseline is 3, and the description goes beyond the schema by stating a cross-parameter constraint (exactly one of dow, cron, every_days) and by tying task_type "loop" to a follow-up call. It does not explain the interplay of parent_task_id/every for subtasks or task_missed_behavior.

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 immediately qualifies it with per-type semantics ("schedule" needs exactly one of dow, cron or every_days). It also establishes the loop workflow, which helps separate this from create_loop, though it never explicitly contrasts the two.

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 concrete when-to-use routing: use task_type "loop" and then call enqueue_task to place a task in a loop, and the exactly-one-of constraint for schedule tasks. It stops short of naming create_loop or update_task as alternatives for adjacent needs, so the exclusion set is implied rather than stated.

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