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

The description says 'Embed' and returns a new PNG, implying mutation, but the annotation declares readOnlyHint: true. This is a direct contradiction—embedding a watermark is a transform/write-like operation. Additionally, no details about side effects, reversibility, or cost are disclosed beyond the '10 points' note, which is not behavioral transparency. This contradiction severely hampers correct invocation.

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 short and front-loaded with the core purpose. The bilingual wording adds slight redundancy, and the cost note is extra but not distracting. It is appropriately concise with no unnecessary fluff, though the cost note could be viewed as non-essential.

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?

A simple tool with 2 parameters and no output schema; the description clarifies the return format (PNG) and supported input formats. However, it lacks any statement about when to use this tool vs siblings and does not explain behavior like whether the original image is modified (which would help resolve the annotation contradiction). It covers the essentials but leaves usage context vague.

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%, so the schema fully documents both parameters. The tool description provides no additional parameter-level detail beyond what the schema already contains (e.g., code range, URL format). Baseline 3 applies because the description does not compensate for anything missing.

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 action ('Embed an invisible watermark code into an image') and the output ('PNG 이미지를 반환합니다'). It is specific and distinguishes the invisible nature, but does not explicitly differentiate from sibling tools like draw_watermark_image or get_watermark, which would earn a 5.

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?

No guidance on when to use this tool versus alternatives. The description mentions robustness ('이미지가 일부 변형되어도 높은 확률로 워터마크를 확인할 수 있습니다') but does not specify conditions for use or exclusions. The agent would need to infer from the tool name and title.

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