delete_directory

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

Annotations already mark the tool as destructive, so the description adds value by spelling out the two key behavioral constraints: non-empty directories need recursive=true, and the root can never be deleted. It does not contradict the annotations and gives the agent the safety-relevant details it needs.

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?

Two short sentences with no filler. The core delete action and scope come first, followed by the single most important usage condition, so an agent gets the critical information immediately.

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 destructive directory tool, this description is complete: it states what is deleted, the path scope, the recursion requirement, and an absolute safety exclusion. With annotations covering the destructive nature and the schema fully documenting parameters, an agent has everything required to invoke it correctly.

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 100%, with both parameters already described. The description enhances this by attaching a condition to `recursive` (required for non-empty directories) and reinforcing that `path` is interpreted relative to the workspace root, which is behavior the schema alone doesn't fully convey.

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 a specific action and resource ('Delete a directory'), defines the exact scope ('below the configured workspace root'), and clarifies the one condition that changes behavior (recursive on non-empty directories). This makes it clearly distinct from sibling delete_file and other workspace tools.

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?

It provides actionable usage conditions: non-empty directories require recursive=true, and the workspace root is permanently excluded from deletion. It stops short of explicitly naming alternatives such as delete_file for files, but the resource type and conditions make the appropriate context clear.

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