Capture the user's exact Blender 3D viewport as seen in the GUI. For judging the model itself, use look() instead.
Screenshot of the user's 3D viewport exactly as they see it (GUI Blender only). For judging the model itself prefer look(), which is independent of the user's view.
| Name | Required | Description | Default |
|---|---|---|---|
| frame | No | Zoom the user's viewport to fit everything first (changes their view). | |
| max_size | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It usefully discloses the GUI-Blender-only constraint (unavailable in headless), which is real behavioral context, but says nothing about capture latency, resolution limits, or the return format. The view-changing side effect of 'frame' is covered only in the schema, not the description.
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 tight sentences with zero filler, front-loading the primary purpose before routing to the alternative. Every clause 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 screenshot tool with no output schema and no annotations, the description covers purpose, environment, and alternative adequately. Minor gaps remain around the undocumented max_size parameter and what the capture returns, but the core informational needs are met.
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 50%: 'frame' is well documented in the schema, but 'max_size' is undocumented in both schema and description. The description adds no parameter meaning at all, so it neither compensates nor enhances beyond the structured fields.
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+resource ('Screenshot of the user's 3D viewport exactly as they see it') with precise scope ('exactly as they see it'), and explicitly distinguishes itself from the sibling look(), which also captures model imagery.
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?
Names the alternative (look()) and the exact condition selecting it ('For judging the model itself prefer look(), which is independent of the user's view'), plus the environment restriction '(GUI Blender only)'. When-to-use, when-to-use-alternative, and an availability constraint are all present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.