螢幕截圖

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

Since no annotations are provided, the description carries the full burden. It discloses the core behavior (captures full screen), the return type (PNG), and the ability for multimodal clients to directly view the image. This is above the minimum viable, though it does not mention permissions or potential capture of sensitive content, which would be ideal.

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 exceptionally concise: two sentences, front-loaded with the primary action, followed by the return format and a usage guideline. Every sentence serves a purpose with no waste. Ideal structure for a simple tool.

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 is largely complete for a parameterless tool: it states what it does and returns. However, it leaves minor ambiguity about whether 'full-screen' includes multiple monitors or just the primary display. It also omits any note on error conditions, though this is not critical for such a simple action.

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?

With zero parameters, the baseline is 4. The description does not need to add parameter semantics, and it does not attempt to. It correctly leaves an empty schema; the description's mention of full-screen capture aligns with the no-parameter design.

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 verb (capture) and resource (local full-screen), and specifies the output format (PNG image). It is distinct from sibling tools like list_windows and read_clipboard, and the scope ('full-screen') differentiates it from per-window operations. No tautology or ambiguity.

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 provides a usage rule: 'call only when explicitly needed' (僅在明確需要時呼叫). This is a conditional guideline, but it does not compare with alternatives (e.g., list_windows for window titles or read_clipboard for text). It implies careful usage but lacks explicit when-to-use-vs-other guidance.

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