Skip to main content
Glama

dialogbrain

by com.dialogbrain
OverviewDiscussionsAdmin

tasks_create

Create a task in this workspace. Leave the assignee empty to put it in the backlog, or name someone to hand it over.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTask title
due_atNoISO datetime when the task is due, e.g. '2026-03-31T15:00:00Z'. A time without a zone is read as UTC.
tag_idsNoTopics for the task: ids of workspace tags that apply to tasks (ai_tags.list with applies_to='task'). Replaces the current set; [] clears it.
agent_idNoAct as this agent instead of as yourself — the task is recorded as authored by it. Optional.
assigneeNoWho should do this: a workspace member (email, username, or user:<id> as workspace.members lists them), an AI agent (its name), or a contact (display name). Use 'me' for yourself. Call workspace.members to see who can be assigned. Where this listing offers assignee_user_id / assignee_agent_id / assigned_to_contact_id, they name an exact target instead.
due_dateNoDate when task is due (e.g. '2026-03-31'). Use with due_time or alone.
due_timeNoTime when task is due (e.g. '15:00'). Used with due_date.
priorityNoTask priority (default: medium)
thread_idNoRelated thread ID
descriptionNoDetailed description
repeat_unitNoUnit for repeat_every.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
repeat_everyNoMake the task repeat: completing it creates the next occurrence, due this many repeat_unit after the previous deadline. E.g. repeat_every=3, repeat_unit='month' for quarterly.
target_sessionNoWhich desktop Claude session should run this, by the name shown in workspace.desktops. Only needed when the assignee is an AI agent that runs on a machine and more than one session is connected — otherwise the task is not dispatched at all, rather than sent to a machine you did not mean.
assignee_user_idNoExact workspace member to assign to
assignee_agent_idNoExact AI agent to assign to
attachment_file_idsNoFile IDs to attach (from files.upload)
assigned_to_contact_idNoExact contact to assign to

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / assignee / description
      Previous value: -"Who should do this: a workspace member (email or username), an AI agent (its name), or a contact (display name). Use 'me' for yourself. Call workspace.members to see who can be assigned. For an exact target, pass assignee_user_id / assignee_agent_id / assigned_to_contact_id instead."New value: +"Who should do this: a workspace member (email, username, or user:<id> as workspace.members lists them), an AI agent (its name), or a contact (display name). Use 'me' for yourself. Call workspace.members to see who can be assigned. Where this listing offers assignee_user_id / assignee_agent_id / assigned_to_contact_id, they name an exact target instead."
  2. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
+  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+  "type": "integer"
+}
  3. 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-idempotent, non-destructive write confined to the workspace, so the safety profile is covered. The description adds the only meaningful extra trait — that an empty assignee routes the task to a backlog rather than the caller — but says nothing about side effects like notification/dispatch, permission needs, or duplicate-submission behavior for a non-idempotent create.

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?

Two short sentences with no filler; the core action is front-loaded and the assignment guidance follows immediately. Every clause carries information an agent needs.

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 18-parameter tool with full schema descriptions, complete annotations, and no output schema, the description covers the essential create-vs-assign decision and nothing critical is missing. It could have noted recurrence or agent-dispatch behavior, but the schema already carries those details adequately.

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% with rich per-parameter prose (assignment forms, repeat semantics, target_session dispatch), so the baseline is 3. The description earns above that by clarifying a rule the schema does not state: omitting assignee places the task in the backlog and naming someone hands it over, which is genuine added meaning for the most consequential parameter.

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+resource ("Create a task in this workspace") and adds the assignment/backlog distinction, which makes the intent unambiguous. It does not name or differentiate itself from sibling write tools like tasks_update or agents_create, but the resource is specific enough to disambiguate in practice.

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?

It gives one actionable usage rule — leave assignee empty for the backlog, name someone to hand it over — which tells the agent how to use the tool in two common cases. It offers no when-not-to-use guidance, no alternative tools, and no prerequisites (e.g. needing workspace membership before assigning), leaving the rest to inference.

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

All dialogbrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources