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

Annotations provide readOnlyHint=true, and the description is consistent with it by stating a new artifact is returned ('삽입한 PDF 를 반환합니다') rather than implying mutation of the source. Beyond the annotation, the description adds useful behavioral facts: adjustable properties, PDF-only restriction, and a 10-point-per-call cost. No contradiction exists between the write-looking action ('draw') and the read-only hint because the tool returns a processed copy.

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: purpose first, then output behavior, customization options, format constraint, and cost. The only waste is that the Korean sentences largely restate the English ones, creating minor bilingual redundancy, but every substantive fact earns its place.

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 9 parameters, 2 required, full schema coverage, and an annotation covering the safety profile, the description covers the essentials: purpose, output (returns watermarked PDF), customization, and input restriction. Gaps are minor — no explicit mention of failure modes for invalid URLs or guidance on which sibling to use for non-PDF files — but these are partially mitigated by the schema and tool-name context.

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 every parameter already carrying ranges, defaults, and units (e.g., angle 0~360 default 35, density 100~200 default 150). The description's summary of '글자 크기·색상·투명도·각도·밀집도·적용 영역' (font size, color, opacity, angle, density, application area) provides a helpful conceptual grouping but adds no factual meaning beyond the schema, so the high-coverage baseline of 3 applies.

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+resource: 'Draw a visible text watermark across every page of a PDF file.' It names the resource (PDF), the action (draw visible text watermark), and scope (every page). This clearly differentiates the tool from siblings like draw_watermark_image, which applies watermarks to images instead.

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 implies usage by stating the operation ('insert a text watermark across all pages of a PDF') and adds constraints ('PDF 형식의 파일만 허용됩니다' — only PDF files allowed) and cost ('[호출당 10포인트]'). However, it never explicitly routes to alternatives such as draw_watermark_image for non-PDF inputs, so an agent must infer the boundary from tool names rather than from this description.

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