Capture the current Three.js scene as a PNG for visual inspection. Optionally set the image width and height before saving to screenshots/.
[INSPECT] Read-only. Screenshot of the current scene (also saved as PNG in screenshots/).
| Name | Required | Description | Default |
|---|---|---|---|
| width | No | Width in pixels (default: canvas width) | |
| height | No | Height in pixels (default: canvas height) |
Changes observed during successful MCP inspections.
v0.5.0Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / height / descriptionPrevious value: -"Height in pixels"New value: +"Height in pixels (default: canvas height)"Input schema / properties / width / descriptionPrevious value: -"Width in pixels"New value: +"Width in pixels (default: canvas width)"v0.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint, so the safety profile is covered. The description adds a genuinely useful behavioral detail beyond annotations: the screenshot is also persisted as a PNG under screenshots/, revealing a file-system side effect the annotations do not mention.
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 compact lines with the classification and read-only tag front-loaded, followed immediately by what is captured and where it is stored. Every element earns its place with no filler.
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 two-optional-parameter, no-output-schema inspection tool, the description covers what is produced (a screenshot image plus a saved PNG) and the parameters are fully documented by the schema. The only gap is the absence of routing guidance versus sibling capture tools.
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% (both width and height are documented with defaults), so the schema carries the parameter semantics. The description adds nothing about sizing, so the baseline of 3 applies.
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 and resource ('Screenshot of the current scene') with a clear classification tag ([INSPECT] Read-only). However, it does not distinguish itself from close siblings like annotated_screenshot or capture_frames, which an agent would need to choose between.
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 when-to-use or when-not-to-use guidance is given. The description never mentions the nearby alternatives (annotated_screenshot, capture_frames, texture_preview), leaving the agent to infer which capture tool to pick from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.