delete_directory

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

Annotations already declare destructive/not-readOnly/idempotent, but the description adds material context beyond them: recursion, absence of a dry-run, absence of a referencer check, the already_absent idempotency signal, and a warning that the `deleted` flag alone is untrustworthy for verification. This is exactly the operational detail annotations cannot convey.

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?

Front-loads the DESTRUCTIVE warning and the scope, then flows into alternatives, idempotency, verification, and return shape with little waste. The UEditorAssetSubsystem note is slightly tangential but still earns its place as an operational caveat.

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?

With no output schema present, the description supplies the return shape itself ({ path, already_absent, deleted }) and warns which field is unreliable. Combined with the destructive-scope and verification guidance, nothing an agent needs to call this safely is missing.

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 100% and both parameters (path, asset_path) are fully documented in the schema, including the alias relationship and the '/'-prefix requirement. The description adds no parameter syntax or format detail beyond that, so the baseline 3 applies.

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 and resource ('removes a content-browser folder') and immediately scopes it: 'AND every asset inside it, recursively.' It goes further by naming the sibling it differs from (bulk_delete_assets) and how, so an agent can distinguish it without opening either schema.

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?

Names the alternative explicitly and characterizes its behavior ('defaults to dry_run and refuses vendored roots'), which tells the agent when each tool is appropriate. It also supplies a post-condition verification procedure ('git status on the corresponding Content/ path'), so the agent knows how to confirm success.

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