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

No annotations are provided, so the description carries the full burden; it does disclose the key trait that subtrees are removed transitively, which is real value. However, it says nothing about irreversibility, whether attached arrows are also removed, or what happens if a node ID is invalid.

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 tight sentence with no filler and the cascade behavior front-loaded. It is perhaps too sparse for a destructive operation, but not verbose.

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 destructive batch operation with no annotations and no output schema, the description covers what is deleted but omits recovery guidance, failure semantics, and confirmation expectations. It is the minimum an agent needs to call it, but not enough to call it safely.

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 coverage is 50%: projectId is richly documented in the schema (including the Canvas-URL tip), while nodeIds has no schema description. The phrase "one or more nodes" implies batch-array semantics for nodeIds, which is a modest addition but does not explain element format or behavior on missing IDs.

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+resource ("delete ... nodes") and adds the important scope detail that entire subtrees are removed. The verb naturally separates it from add_nodes, move_nodes, and update_node, though it does not explicitly name a sibling.

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?

There is no statement of when to use this tool versus update_node (to modify) or move_nodes (to relocate), and no preconditions such as required permissions or confirmation steps. The agent is left to infer that this is the destructive path.

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