watermark_image

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

With no annotations provided, the description carries the full burden. It explicitly says the tool 'generates watermarking metadata and instructions' rather than actually modifying the image, which is a key behavioral trait. It also discloses the return type (dictionary with metadata, instructions, compliance info) and mentions the watermark must be machine-readable and detectable. This provides useful transparency without contradicting any 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 organized into short sections (Args, Returns, Example) with the core purpose front-loaded in the first sentence. It is slightly longer than strictly necessary due to the example, but every sentence contributes useful information, making it efficient rather than 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?

For a tool with three params, a simple dictionary output, and no annotations, the description is highly complete. It includes the regulatory reference (Article 50(2)), the output shape, parameter semantics, and a worked example. The presence of an output schema means return values need not be detailed further, and the description provides enough context for an agent to select and invoke the tool correctly.

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%, so the description must compensate. It does: each parameter is explained clearly (image_description, generator, format_type), including example values for generator ('DALL-E', 'Midjourney') and format_type ('png', 'jpg', 'webp') with a default. The example call demonstrates usage. This adds real meaning beyond the schema's bare property names and defaults.

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 first sentence 'Generate watermarking metadata for AI-generated images per Article 50(2)' clearly states a specific verb ('generate') and resource ('watermarking metadata for AI-generated images'), distinguishing it from sibling tools like watermark_text, watermark_video, and watermark_audio by explicitly scoping to images. The mention of C2PA compliance adds further specificity.

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 clearly indicates this tool is for AI-generated images, providing context that it produces C2PA-compliant metadata and instructions. However, it does not explicitly mention when not to use this tool or point to alternatives (e.g., watermark_text for text), though sibling names make the distinction implicit. This fits the 'clear context, no exclusions' level.

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