Inspect the actual rendered image to verify edits, zoom into specific regions, isolate individual layers, or overlay a measurement grid.
LOOK at the result: the real rendered image. box=[x,y,w,h] zooms on a detail (document px). layer= shows that layer alone. grid=true overlays a 10% grid labelled in document px.
| Name | Required | Description | Default |
|---|---|---|---|
| box | No | ||
| grid | No | ||
| layer | No | ||
| width | No | ||
| project | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It implies a read/render operation and describes the visual output, but never states that it is non-mutating, whether it consumes compute/credits, whether it can be slow, or in what form the image is returned. The render verb tells the agent what comes back but not the operational traits.
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?
It is three tight sentences with the core purpose front-loaded before the parameter notes. The terse notation (box=[x,y,w,h], layer=<id>, grid=true) is efficient, though it is compressed enough to read as notes rather than prose.
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?
With no annotations, no output schema, and 0% schema coverage across five parameters, the description leaves real gaps: the meaning of width and project is never stated, and there is no indication of the return payload despite there being no output schema to fall back on. It covers the interesting visual parameters but not enough for an agent to call the tool confidently in all cases.
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 0%, so the description must compensate, and it does document three of five parameters with non-obvious detail: box as [x,y,w,h] in document pixels, layer as a single-layer solo, and grid as a 10% overlay labelled in document px. However, width (default 1024) and project are entirely unexplained in both schema and description.
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 states the tool produces the rendered raster preview via the imperative 'LOOK at the result: the real rendered image,' which distinguishes it from the AI-analysis siblings (analyze_image, describe_image, review_image) that operate on images rather than render them. It names no sibling explicitly, so differentiation is implicit rather than stated.
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?
There is no when-to-use or when-not-to-use guidance. The agent is told what box, layer, and grid do, but nothing indicates when a preview is the right call versus export_image, analyze_image, or review_image, or whether it must be preceded by other state-changing calls.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.