Done Bear

Add Task

task_add

Create a new task. The when parameter controls which GTD view it appears in: today (default), inbox, upcoming, anytime, or someday. A new task lands in Today unless you say otherwise, so pass when: "inbox" for a capture the user has not committed to doing today. Because the default is date-dependent, always pass the user's timezone — without it today is resolved in UTC. Dates use YYYY-MM-DD format. Optionally set an assignee, attach existing labels, and create checklist items at creation. For a task with sub-items (e.g. a shopping list), pass them in checklist in one call: their order is preserved exactly. The result names the view the task landed in. This only creates: to change a task that already exists use task_edit (fields) or checklist (items), and search first when the user may be describing a task they already have.

Input Schema

TableJSON Schema

Name	Required	Description
`team`	No	Team id, key, or name
`when`	No	GTD view bucket: today, inbox, upcoming, anytime, someday. Omitting this means today, with three exceptions: a deadline or a missing timezone falls back to anytime (the work is due later, or today cannot be resolved), and a project or team falls back to inbox (the task is already filed). Pass timezone to get today. Use "inbox" for a capture the user has not committed to doing.
`notes`	No	Task description/notes
`title`	Yes	Task title
`labels`	No	Labels to attach (each a label id, title, or id prefix)
`context`	Yes	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
`project`	No	Project id, key, or name to assign this task to
`assignee`	No	Member user id, name, or email to assign the task to
`deadline`	No	Due date in YYYY-MM-DD format
`timezone`	No	IANA timezone used to resolve "today" for views and scheduling (e.g. Australia/Melbourne). Defaults to UTC, which misclassifies Today/Upcoming for users in other timezones, so always pass the user's timezone when known.
`checklist`	No	Checklist item titles to create on the task, kept in the given order
`workspace`	No	Workspace id, slug, or name
`idempotency_key`	No	Stable key that makes retries safe: repeated calls with the same key create only one record and return the same id.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes
`ok`	Yes
`view`	Yes
`title`	Yes
`number`	Yes
`checklistCount`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A5/5.0

Behavior5/5

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

Discloses important behavioral details beyond annotations: default placement in Today, timezone-dependent resolution of 'today' (UTC fallback), three exceptions that change the default view (deadline, missing timezone, project/team), checklist order preservation, and that the result names the landed view. Annotations are minimal (all false), so the description carries the full burden and succeeds.

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 compact yet information-dense. Every sentence contributes: purpose, view behavior, timezone caveat, date format, optional fields, checklist handling, result naming, and sibling routing. It front-loads the core purpose and key behavioral caveats before enumerating options. No filler or redundancy.

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

Completeness5/5

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

Given 13 parameters, an output schema, and minimal annotations, the description covers all critical operational details: default behavior, exceptions, timezone handling, date format, optional fields, checklist semantics, result content, and when to use alternatives. An agent can confidently invoke this tool without ambiguity. The output schema handles return details, so nothing critical is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds substantial semantic value: explains `when` enum behavior with default and exceptions, clarifies that `timezone` must be passed to resolve 'today' correctly, notes checklist order is preserved, and mentions idempotency_key makes retries safe. It goes well beyond the schema's per-property 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 opens with 'Create a new task' – a specific verb and resource. It immediately differentiates from sibling tools by explicitly naming task_edit, checklist, and search as alternatives for modification, sub-items, and existing-task discovery. No ambiguity about what this tool does.

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

Usage Guidelines5/5

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

Provides explicit when-to-use guidance: 'This only creates: to change a task that already exists use task_edit (fields) or checklist (items), and search first when the user may be describing a task they already have.' It also explains the `when` parameter's role in GTD views and when to pass `when: "inbox"` for captures. The timezone requirement is clearly stated with a reason.

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

All Done Bear tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?