Create a new .canvas file in an Obsidian vault, optionally including initial nodes and edges to visualize connections.
Create a new .canvas file with optional initial nodes/edges.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| edges | No | ||
| nodes | No |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey that this is a mutating (readOnlyHint=false) and non-destructive operation; the description's 'Create a new' is consistent with them. It adds little beyond the resource type — no disclosure of what happens if the target path already exists, overwrite behavior, or side effects — but with annotations present, the bar is lower and no contradiction exists.
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?
A single, front-loaded sentence with zero waste; it states the action, resource, and the optional parameters in 13 words. Every word earns its place.
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 simple create-with-optional-content tool this is adequate, but with no output schema and 0% param coverage, key facts are left out: behavior when the file exists, the serialization format of the nodes/edges strings, and what the tool returns. The sibling set (list_canvases, read_canvas, add/update/remove node/edge tools) makes the tool's role clear, but the call contract is under-specified.
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?
Schema description coverage is 0%, so the description must carry parameter meaning. It clarifies that nodes and edges are optional and represent initial content, which maps to the two nullable params, but it does not specify the expected string format (e.g., JSON-serialized arrays/objects) or what 'path' refers to. This only partially compensates for the coverage gap.
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?
States a specific verb ('Create') and resource ('.canvas file'), and the qualifier 'new' distinguishes it from sibling tools like add_canvas_node/add_canvas_edge that modify existing canvases. It could be stronger by explicitly naming the sibling it is not, but the resource type alone disambiguates it from create_note/create_daily_note.
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 implies use for brand-new canvases and that nodes/edges are optional initial content, which roughly signals when to use it versus add_canvas_node/add_canvas_edge. However, it gives no explicit guidance, exclusions, or mention of when to prefer the sibling mutation tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.