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

Annotations provide readOnlyHint=true, and the description does not contradict it; it returns a new PNG rather than mutating the original. The description adds useful behavioral context beyond the annotation: the watermark is invisible, robust to partial transformations, supports multiple formats, and costs 10 points per call. It does not detail failure modes, but the addition of cost and robustness is meaningful.

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 and front-loaded with the main action in English, followed by Korean translation and key operational facts (return type, robustness, supported formats, point cost). Every sentence contributes meaningful information; the only slight inefficiency is the bilingual repetition of the same core statement.

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 two simple parameters and no output schema, the description covers the input domain well and states the output is a PNG image. However, it does not specify how the returned image is delivered (e.g., URL, base64, file path) or whether the operation is synchronous. Given no output schema exists, a more explicit return-value description would complete the picture.

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, so the baseline is 3. The description adds valuable semantics beyond the schema: code is described as a numeric watermark code with a specific intended range (1 ~ 21,767,823,359), and image_url is clarified with allowed MIME types and a 50MB size limit. A minor inconsistency exists between the schema's broad min/max and the description's restricted range, but the description still provides actionable detail.

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 a specific verb and resource: 'Embed an invisible watermark code into an image' and clarifies the return type (PNG image). This makes the tool's function clear and conceptually distinguishes it from get_watermark (extraction) and draw_watermark_image/PDF (likely visible watermark drawing), though it does not explicitly name or contrast siblings.

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 gives implied usage context: it is for inserting an invisible, robust watermark into common image formats, and notes that detection works even after partial image modification. However, it provides no explicit guidance on when to prefer this tool over sibling draw_watermark_image or get_watermark, nor any 'when not to use' conditions.

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