anti_ai_sanitize

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

With no annotations, the description carries the full behavioral burden and largely succeeds: it discloses metadata stripping, watermark disruption, camera-physics injection, and parameter-specific effects such as Lanczos resampling and sensor-grain noise. It stops short of noting side effects like whether the original file is modified, but the core behavior is clearly exposed.

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 summary line is front-loaded and informative, followed by a tight per-parameter list. For 8 parameters, the length is justified and every sentence adds value beyond the schema.

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?

The description covers required input, all optional parameters, defaults, and the return value effectively. It lacks explicit sibling routing and edge-case or failure notes, but the parameter detail is sufficient for correct invocation.

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 0%, and the description fully compensates. Every parameter gets a purpose, default, and often details absent from the schema, such as grain_intensity range (1.0-2.5), camera_profile enum values, and micro_resample's 0.3% Lanczos behavior.

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 'Full anti-AI pipeline' and immediately names concrete operations: strips C2PA/EXIF, disrupts lattices/watermarks, and adds camera physics. This clearly identifies the resource and action, and distinguishes it from narrower siblings like strip_metadata_only and inject_camera_profile.

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 description does not explicitly state when to use this tool versus alternatives or when not to use it. The 'Full anti-AI pipeline' phrasing and sibling names imply it is the comprehensive option, but the guidance is inferred rather than stated.

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