Delete a file or directory

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

With no annotations, the description carries the full burden; it usefully discloses the file-system permission requirement, which an agent must know. However, it omits key destructive-tool behavior: whether deletion is permanent/recoverable, what happens on a nonexistent path, and whether an undo path exists despite the sibling bb_undo.

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, front-loaded sentences with zero waste; the condition for directory deletion immediately follows the core action.

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 two-param tool with no annotations and no output schema, the description covers the action, the recursive branch, and the permission prerequisite, but leaves irreversibility, error behavior, and undo/alternative tooling unaddressed.

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 0%, so the description must compensate. It explains 'recursive' in behavioral terms (directory deletion), but adds no format, path-resolution, or default semantics beyond the schema's own default:false, leaving 'path' undocumented.

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 ('Delete') and resource ('file', 'directory') and clarifies the branching behavior for directories. It is clearly distinct from file-reading siblings like bb_read_file/bb_list_dir, though it does not explicitly name any sibling it should be chosen over.

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 implies the recursive=true condition for directories, which is useful conditional guidance, but offers no when-to-use/when-not-to-use framing, no references to alternatives (e.g. bb_undo or bb_delete_elements), and no prerequisites beyond permission.

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