rmdir

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

Beyond the destructiveHint annotation, the description adds that it fails safely on non-empty directories and returns JSON with removed paths. It also mentions dry-run support, which is not covered by annotations.

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?

The description is multi-sentence but each sentence adds value: purpose, destructive note, safety, dry-run, return type, and usage guidance. It is front-loaded and not excessively 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?

Given the tool's simplicity (2 parameters, no output schema), the description covers all relevant aspects: purpose, behavior, safety, when to use, alternatives, return format, and dry-run support. No gaps remain.

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 descriptions for both parameters. The description adds context by stating that paths are for 'Empty directories to remove' and that dry-run is for previewing. It also implies failure on non-empty directories, adding value beyond schema.

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 clearly states the tool removes empty directories and distinguishes from sibling tools like 'rm --recursive' for non-empty directories and 'unlink' for files. It specifies the verb 'remove' and the resource 'empty directories'.

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?

Explicitly provides when to use (clean up empty directory trees), when not to use (directories with contents or files), and alternatives ('rm --recursive', 'unlink'). Also mentions dry-run for preview.

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