Capture the 3D viewport as a screenshot file, returning the file path for use in Blender workflows.
Capture a screenshot of the 3D viewport to a file. Returns the file path.
| Name | Required | Description | Default |
|---|---|---|---|
| filepath | No | /tmp/viewport.png |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0+hardened.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds that a file is written and a file path is returned, which is useful, but it does not disclose overwrite behavior, path creation, or filesystem side effects. No contradiction with annotations.
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?
A single, front-loaded sentence of 14 words contains all core information with no filler. Every phrase earns its place, and the primary action is stated immediately.
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 one-parameter tool with a default value, read-only annotation, and existing output schema, the description plus schema is nearly sufficient for correct invocation. The main missing piece is the distinction from render_viewport, which affects tool selection more than calling mechanics.
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?
The filepath parameter has no schema description (0% coverage), but the phrase 'to a file' and 'Returns the file path' loosely imply that the parameter controls the output location. It does not explicitly name the parameter or explain defaults/format, so compensation is only partial.
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 uses a specific verb ('Capture') and a specific resource ('3D viewport'), and states the output ('file path'). It is clearly not a tautology. However, it never contrasts with the sibling render_viewport tool, so an agent must infer that a screenshot differs from a render.
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?
No guidance is provided on when to use capture_viewport instead of render_viewport, render_image, or get_viewport_info. There are no conditions, exclusions, or alternative routing signals; the agent is left to infer selection from the name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.