Skip to main content
Glama
lavalava45

PaintPilot

by lavalava45
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

photoshop_guard_review_image

Deliver stored exact-image evidence for a completed PaintPilot visual Guard operation, including per-role metadata, so you can review required images before submitting observations.

Instructions

Deliver stored exact-image evidence for a completed visual Guard operation; use photoshop_get_preview for a fresh document preview instead. Obtain operation_id from photoshop_guard_cycle_auto or its completed job result. Returns JSON review instructions, operation_id and per-role delivery/omission metadata, plus MCP image blocks with recorded MIME types (normally JPEG); roles and image count depend on the stored review package. Omit roles for all required images, or request only missing roles. Already delivered exact images may be reused as confirmed same-chat references without resending bytes. Does not paint or capture a replacement frame, but records delivery receipts/timing and updates the review cache; delivery is not proof of visual observation. Inspect the actual images before submitting previous_observation through cycle_auto. review_scope=whole-scene requests whole-scene review metadata using the same images. Force redelivery only for unavailable/failed images with redelivery_reason; repeated forced delivery is rejected. Missing previews or invalid roles return isError=true with an error code; incomplete delivery lists undelivered_roles and next_required_action, not successful visual review.

Input Schema

NameRequiredDescriptionDefault
rolesNoOptional roles, e.g. after/after_crop; omit to deliver all required images.
document_idNoOptional Photoshop document id from photoshop_get_state / photoshop_list_documents. When set, the tool verifies that this document is already active and fails closed if another tab is active. It never switches the active Photoshop document automatically.
operation_idYesExact visual operation_id from photoshop_guard_cycle_auto or its completed job result, with a stored durable review preview. Not a job_id; historical images do not authorize current-frame continuation.
review_scopeNoRequest whole-scene Critic/editable-scope metadata for retained-frame re-evaluation, final completion or replacement confirmation using the same exact images; cached deliveries are reused.
force_redeliveryNoOnly for unavailable/failed images; requires redelivery_reason. Same-operation exact delivered images in a host-proven chat are reused without claiming visual observation.
redelivery_reasonNoRequired when force_redelivery=true: images-unavailable means the client cannot access the images; delivery-failed means image delivery failed. Never use for routine confirmation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.8.2
    • addedInput schema / properties / operation_id / description
      Added value: +"Exact visual operation_id from photoshop_guard_cycle_auto or its completed job result, with a stored durable review preview. Not a job_id; historical images do not authorize current-frame continuation."
    • addedInput schema / properties / redelivery_reason / description
      Added value: +"Required when force_redelivery=true: images-unavailable means the client cannot access the images; delivery-failed means image delivery failed. Never use for routine confirmation."
  2. First observedv1.8.0-preview.1

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discloses key traits: the return format (JSON review instructions plus MCP image blocks with recorded MIME types), side effects ('records delivery receipts/timing and updates the review cache'), what it does not do ('does not paint or capture a replacement frame'), error behavior ('returns isError=true with an error code' and lists undelivered_roles and next_required_action), and the caveat that 'delivery is not proof of visual observation'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and alternatives, and every sentence carries operational information. It is dense but not wasteful; some sentences are long but structured with semicolons and clear delimiters, keeping it from becoming rambling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (six parameters, no annotations, no output schema), the description is thorough: it covers purpose, when to use, return format, side effects, error behavior, and constraints. An agent has everything needed to invoke it correctly without needing additional documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents all six parameters. The description adds minor context (e.g., 'request only missing roles') but largely restates or implies semantics already present in the schema. A baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Deliver stored exact-image evidence for a completed visual Guard operation', and immediately distinguishes it from the sibling photoshop_get_preview by saying to use that for a fresh preview instead. An agent can tell exactly what this tool does and doesn't do.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use this tool versus the alternative (photoshop_get_preview), where to get operation_id (photoshop_guard_cycle_auto), how to handle roles ('Omit roles for all required images, or request only missing roles'), and the restricted condition for force_redelivery ('only for unavailable/failed images'). This leaves no ambiguity about when and how to invoke it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools