lookRender an artboard with measured facts, or compare a region with a reference.
| Name | Required | Description | Default |
|---|---|---|---|
| flow | No | ||
| brief | No | ||
| scale | No | ||
| region | No | Artboard-local crop. | |
| artboard | No | ||
| critique | No | ||
| artboards | No | ||
| before_after | No | ||
| reference_id | No | From set_reference_image. | |
| inspect_shape | No | Path whose anchors come back artboard-local. | |
| reference_region | No | Reference crop when it differs from region. |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / artboard / anyOfPrevious value: -[
- {
- "maximum": 9007199254740991,
- "minimum": 0,
- "type": "integer"
- },
- {
- "maxLength": 120,
- "type": "string"
- }
-]New value: +[
+ {
+ "type": "integer"
+ },
+ {
+ "type": "string"
+ }
+]Input schema / properties / artboards / items / anyOfPrevious value: -[
- {
- "maximum": 9007199254740991,
- "minimum": 0,
- "type": "integer"
- },
- {
- "maxLength": 120,
- "type": "string"
- }
-]New value: +[
+ {
+ "type": "integer"
+ },
+ {
+ "type": "string"
+ }
+]Input schema / properties / artboards / minItemsRemoved value: -1Input schema / properties / brief / descriptionRemoved value: -"One paragraph for the optional reviewer; retained for this project."Input schema / properties / brief / maxLengthRemoved value: -4000Input schema / properties / brief / minLengthRemoved value: -1Input schema / properties / inspect_shapeAdded value: +{
+ "description": "Path whose anchors come back artboard-local.",
+ "type": "string"
+}Input schema / properties / reference_idAdded value: +{
+ "description": "From set_reference_image.",
+ "type": "string"
+}Input schema / properties / reference_regionAdded value: +{
+ "anyOf": [
+ {
+ "properties": {
+ "height": {
+ "type": "number"
+ },
+ "width": {
+ "type": "number"
+ },
+ "x": {
+ "type": "number"
+ },
+ "y": {
+ "type": "number"
+ }
+ },
+ "required": [
+ "x",
+ "y",
+ "width",
+ "height"
+ ],
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Reference crop when it differs from region."
+}Input schema / properties / region / additionalPropertiesRemoved value: -falseInput schema / properties / region / descriptionPrevious value: -"Crop this rectangle, artboard-local (0,0 is the artboard's top-left)."New value: +"Artboard-local crop."Input schema / properties / region / properties / height / exclusiveMinimumRemoved value: -0Input schema / properties / region / properties / width / exclusiveMinimumRemoved value: -0Input schema / properties / scale / descriptionRemoved value: -"Zoom, up to 4 (8 with region). Omit to let the preview pick."Input schema / properties / scale / exclusiveMinimumRemoved value: -0Input schema / properties / scale / maximumRemoved value: -8Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. Beyond that the description adds only "measured facts," with no disclosure of what is returned (image? structured facts?), how brief/critique/before_after alter behavior, or cost/latency implications of rendering. With no output schema, more burden falls on the description than it carries.
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?
The single sentence is front-loaded and free of filler, which is good. But for an 11-parameter, multi-mode tool it is under-specified rather than concise — appropriate sizing is not achieved.
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?
Eleven optional parameters, nested objects, no output schema, and a 36% description coverage rate demand substantially more explanation than one sentence. An agent cannot tell from this description what most flags do or what the call produces.
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 only 36% across 11 parameters, so the description must compensate and largely does not. Only region/reference comparison is implied; scale, brief, critique, flow, before_after, artboards, and inspect_shape are entirely unexplained in both places.
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 names a verb and resource ("render an artboard") and a second mode ("compare a region with a reference"), which is more than the bare name "look". But the schema reveals many more modes (brief, critique, flow, before_after, inspect_shape) that the description never hints at, so the stated purpose understates the tool's actual scope. It also does not differentiate from overlapping siblings like read_screen, compare_drawing, or export_artboard.
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 an implicit render-vs-compare split, but no explicit when-to-use, when-not-to-use, or named alternative. An agent choosing between this, read_screen, compare_drawing, and export_artboard gets no routing signal from the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.