things3-mcp-server

Overview Schema Source Related Servers Discussions Admin

create_todo

Add a new task to Things 3 with a required title and optional notes, tags, schedule, deadline, project, or area, placing it in the Inbox unless a project or area is specified.

Instructions

Create a new Things 3 to-do.

Input Schema

TableJSON Schema

Name	Required	Description
`area`	No	Area to file the task in (must exist). Ignored if `project` set.
`tags`	No	Comma-separated tag names (e.g. "48h-Liste,Wichtig").
`when`	No	Schedule — "today", "tomorrow", "anytime", "someday" or an ISO date "YYYY-MM-DD".
`notes`	No	Optional notes body.
`title`	Yes	Task title (required).
`project`	No	Project to file the task in (must exist). Takes precedence over `area`. If neither is given the task lands in the Inbox.
`deadline`	No	Deadline (due date) as ISO date "YYYY-MM-DD".

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv0.3.0Aug 21, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / area / description

Added value: +"Area to file the task in (must exist). Ignored if `project` set."

removedInput schema / properties / area / title
```
Removed value: -"Area"
```

addedInput schema / properties / deadline / description

Added value: +"Deadline (due date) as ISO date \"YYYY-MM-DD\"."

removedInput schema / properties / deadline / title
```
Removed value: -"Deadline"
```
addedInput schema / properties / notes / description
```
Added value: +"Optional notes body."
```
removedInput schema / properties / notes / title
```
Removed value: -"Notes"
```

addedInput schema / properties / project / description

Added value: +"Project to file the task in (must exist). Takes precedence\nover `area`. If neither is given the task lands in the Inbox."

removedInput schema / properties / project / title
```
Removed value: -"Project"
```

addedInput schema / properties / tags / description

Added value: +"Comma-separated tag names (e.g. \"48h-Liste,Wichtig\")."

removedInput schema / properties / tags / title
```
Removed value: -"Tags"
```
addedInput schema / properties / title / description
```
Added value: +"Task title (required)."
```
removedInput schema / properties / title / title
```
Removed value: -"Title"
```

addedInput schema / properties / when / description

Added value: +"Schedule — \"today\", \"tomorrow\", \"anytime\", \"someday\" or an ISO\ndate \"YYYY-MM-DD\"."

removedInput schema / properties / when / title
```
Removed value: -"When"
```
removedInput schema / title
```
Removed value: -"create_todoArguments"
```
removedOutput schema / title
```
Removed value: -"create_todoDictOutput"
```

First observedv0.2.1Jul 10, 2026

TDQS

B3.4/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says a to-do is created, but it does not mention what happens in the system, whether the new to-do lands in the Inbox unless area/project is supplied, whether duplicate creates are possible, or what failure conditions matter.

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?

This is a single focused, front-loaded sentence with no filler or repeated information. It is appropriately sized for a tool whose parameter details are already handled by a thorough schema.

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 create operation, the description plus a fully documented schema gives enough information to invoke the tool correctly. An output schema exists, so return-value explanation is not required. The main gap is usage context relative to sibling tools, which is not critical for successful invocation.

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% across all 7 parameters, so the baseline is 3. The description itself adds no parameter-level nuance, but it does not need to because the schema already explains defaults, precedence, date formats, and tag syntax.

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 clearly uses a specific verb ('Create') and names the exact resource ('a new Things 3 to-do'). The word 'new' distinguishes it from sibling tools like update_todo, complete_todo, and cancel_todo without any need to inspect schemas.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this tool versus alternatives. It does not mention that updates should go to update_todo, completion to complete_todo, or cancellation to cancel_todo, so the agent must infer usage context from the tool name and schema.

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

Deploy Server