batch_sanitize_directory

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains that images undergo anti-AI processing but does not state whether originals are modified when output_directory is omitted, whether files are overwritten, or what side effects occur. It also does not disclose format support or failure behavior.

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 compact, with a one-sentence purpose followed by a short parameter list and a returns note. It repeats default values already present in the schema, but overall it is well organized and easy to scan.

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?

As a batch mutation tool with no annotations, this description leaves important operational details uncovered: overwrite semantics, what happens if output_directory is null, whether directories are created, and how errors across multiple images are reported. The output schema exists but is not shown, and the 'Returns' line is too thin to fill this gap.

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?

Although schema description coverage is 0%, the description's Args section adds useful meaning for all four parameters: directory_path is the input source, output_directory is an optional save target, camera_profile is injected, and grain_intensity controls sensor noise. It does not fully specify expected formats or effects, but it meaningfully supplements the raw 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 names a specific action ('Sanitizes all images in a target directory') and a distinct purpose ('anti-AI detection processing'). It is clear that this is a batch operation, which helps distinguish it from single-file siblings like anti_ai_sanitize, though it does not explicitly name those alternatives.

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?

The directory-based scope and processing intent imply the tool is for batch sanitization, and the parameters indicate optional output handling. However, there is no explicit guidance about when to choose this tool versus strip_metadata_only, inject_camera_profile, or single-file processing.

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