スクリーンショット

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

Annotations already declare readOnlyHint=true. The description adds valuable behavioral context: mode differences (Playing captures game camera, Editor uses fly camera) and that it shares camera with dx12_project_world_to_screen. No contradiction.

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 concise (3-4 sentences) and well-structured: action first, then purpose, then mode details. Every sentence adds value with no redundancy.

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 simple zero-parameter tool with readOnly annotations, the description covers all necessary context: behavior, use case, mode differences, and return info. No gaps.

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?

No parameters exist, so schema coverage is 100%. The description adds value by outlining the return information (path/width/height) even without an output schema, helping the agent understand what to expect.

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 it exports the scene view as a PNG and returns path/width/height, specifically for AI to verify operations. It distinguishes from siblings like dx12_screenshot_game_view (by mentioning 'scene view') and links to dx12_project_world_to_screen.

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?

It explains when to use (AI checking results) and notes mode-dependent behavior (Playing vs Editor). However, it doesn't explicitly mention when not to use or alternative tools like dx12_focus_and_screenshot.

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