blender_viewport

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

No annotations exist, so the description carries full responsibility. It discloses key behavior: uses OpenGL viewport capture, not a full render engine, and caps the longest edge. As a capture, side effects are minimal, and the non-render clarification is the most important behavioral trait; nothing contradicts.

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?

Two short sentences that front-load the action and then add the essential 'not a full render' caveat. No filler words.

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 single-parameter, read-only capture tool, the description covers what it does and what it avoids. The only minor gap is the lack of explicit output carry-back (file path vs. data), but the PNG output is stated, so it is adequate.

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 description coverage is 100% with a full explanation of maxEdge (default, max, exclusive minimum). The description adds no parameter details, which is fine under the baseline; no compensation needed.

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?

States a specific verb ('Capture') and resource ('current 3D viewport') with the output format ('PNG') and method ('OpenGL'). The clarification 'Does not run a full render' distinguishes it from a render tool, and the sibling list (health, exec, scene_info) makes it clearly a snapshot utility.

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?

Gives clear context that it captures the viewport rather than executing a full render, which implies use for quick previews. It does not explicitly name an alternative tool or condition, but the scope statement is sufficient given how different the siblings are.

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