Capture the current After Effects comp, Premiere frame at the playhead, Photoshop document, or Illustrator artboard as an image for a visual self-check.
Look at what any app currently shows: AE comp frame, Premiere frame at playhead, Photoshop document, or Illustrator artboard — returned as an image for a quick visual self-check.
| Name | Required | Description | Default |
|---|---|---|---|
| app | Yes | ||
| time | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds value annotations don't: the return is an image (not structured data) and what exactly is captured per app (comp frame vs playhead frame vs document vs artboard). It does not mention resolution, latency, or whether it works on background/hidden documents.
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 sentence, front-loaded with the core action, with the per-app enumeration and return type packed in without filler. 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?
No output schema exists, and the description correctly states the return is an image. Annotations cover safety. The remaining gaps are the undocumented `time` parameter and the unaddressed relationship to ps_preview, which keep it from being fully complete for a 2-parameter cross-app tool.
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 — it partially does by mapping the `app` enum values to their capture semantics (ae→comp frame, pr→playhead, ps→document, ai→artboard). However the `time` parameter is never mentioned in either the schema or the description, leaving its format and role (seconds? frames? AE only?) undocumented.
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?
Specific verb ("look at what any app currently shows") plus concrete per-app resource scoping: AE comp frame, Premiere frame at playhead, Photoshop document, Illustrator artboard. An agent immediately knows this is a cross-app visual capture tool rather than a state getter like ps_getState or ae_getCompState.
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?
The phrase "quick visual self-check" implies the use case (verifying a change visually), which is useful but not framed as when-to-use-vs-alternative. Critically, the sibling ps_preview appears to overlap for Photoshop, and the description does not say when to choose either tool, leaving the agent to guess.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.