Legt ein neues Board an. mode="kanban" (Spalten) oder "canvas" (Pinnwand, Standard). Bei Kanban koennen eigene Spalten angegeben werden, sonst To Do / In Arbeit / Fertig.
| Name | Required | Description | Default |
|---|---|---|---|
| icon | No | Optional: Emoji | |
| mode | No | ||
| name | Yes | ||
| columns | No | Nur bei mode=kanban: Spaltennamen |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses that mode defaults to canvas, that kanban uses columns, and the default column names are 'To Do / In Arbeit / Fertig'. However, it does not describe the return value (e.g., whether a board ID is returned), permissions, or side effects beyond creation. This partial disclosure merits a mid-range score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that packs all essential information: purpose, mode semantics, and column behavior. There is no fluff or redundancy, and the structure is clear and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a creation tool with 4 parameters and no output schema, the description covers core behavior (modes, columns, defaults) effectively. The main gap is the lack of any mention of the return value or what happens after creation, which is a minor omission given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers icon and columns but not name or mode. The description adds crucial meaning to mode (explains 'kanban' and 'canvas' options) and columns (only for kanban, with default column names). This compensates for the 50% schema coverage and clarifies the conditional behavior of columns.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Legt ein neues Board an' (creates a new board), clearly identifying the verb and resource. It further distinguishes the tool by explaining the two modes (kanban vs canvas) and their defaults, which differentiates it from sibling create_* tools (e.g., create_tracker).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use which mode (kanban with custom columns, canvas as default), but does not explicitly discuss when NOT to use this tool or mention alternatives such as create_tracker. It implies usage when creating a board, but lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action (board, column, card, tracker, field, entry) with no overlapping purposes. Even closely related operations like add_card vs add_entry operate on different entity types.
Tool names consistently follow a verb_noun pattern (e.g., create_board, add_card, delete_entry, update_tracker). The mix of 'create' for top-level entities and 'add' for sub-entities is a minor deviation but still predictable.
24 tools is somewhat high but well-justified given the server covers two resource families (boards and trackers) with full lifecycle operations. Each tool has a clear role in the overall surface.
The tool set provides comprehensive CRUD coverage for boards, columns, cards, trackers, and entries. The main gap is the lack of an update_field tool, but this can be worked around by deleting and recreating fields.