Skip to main content
Glama
Sign In
PaintPilot

PaintPilot

by lavalava45
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

photoshop_analyze_value_structure

Analyze a pinned Photoshop document's light/dark value structure and materialize grayscale evidence for Director review. Returns full grayscale and low-frequency images to verify major forms.

Instructions

Analyze large-form light/dark structure when Director value/refinement review needs grayscale evidence; use photoshop_get_preview for ordinary color inspection and photoshop_guard_review_image for stored operation review images. Requires pinned document_id. In Guard, analyzes the exact delivered current frame and automatically registers materialized grayscale/luminance evidence; standalone preview-only catalogs capture a non-destructive preview instead. Returns two MCP JPEG images (full grayscale and low-frequency thumbnail), source/derived SHAs, dimensions and descriptive luminance summaries; Guard also returns a real evidence_operation_id and director_evidence_fields for Director updates. The thumbnail suppresses small texture/noise so major-form claims can be checked independently of surface activity. Writes derived JPEG files when a materialization path is available and registers Guard evidence, but does not modify the PSD or declare artistic PASS. Inspect both images before making an observed claim. materialize_path must be absolute; invalid paths or unavailable preview images fail, and overwriting the source frame is forbidden.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "document_id": "<document_id>"
    },
    "name": "photoshop_analyze_value_structure"
  }
}

Input Schema

NameRequiredDescriptionDefault
document_idYesRequired pinned Photoshop document id whose current preview is analyzed.
materialize_pathNoOptional absolute path where the derived grayscale JPEG should be written for external visual inspection.
max_dimension_pxNoMaximum long edge for a standalone preview capture, default 1000. With a Guard current-frame hook, analyzes those exact stored bytes instead of recapturing/resizing the source.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.8.3
    • addedInput schema / properties / max_dimension_px / description
      Added value: +"Maximum long edge for a standalone preview capture, default 1000. With a Guard current-frame hook, analyzes those exact stored bytes instead of recapturing/resizing the source."
  2. First observedv1.8.0-preview.1

TDQS

A4.8/5.0
Behavior5/5

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

No annotations are provided, and the description carries the full burden well: it discloses that it writes derived JPEG files, registers Guard evidence with a real evidence_operation_id, captures a non-destructive preview in standalone mode, does not modify the PSD or declare artistic PASS, forbids overwriting the source frame, and fails on invalid paths. This is exactly the mutation/authorization/side-effect detail annotations would otherwise cover.

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?

Front-loaded and waste-free in content, with purpose and alternatives first and warnings last. However, it is a single dense paragraph merging selection, behavior, return values, and constraints; bullet-like separation would make it easier for an agent to parse under context pressure.

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?

With no annotations, no output schema, and three parameters, the description covers what it returns (two JPEGs, SHAs, dimensions, luminance summaries, director_evidence_fields), side effects, and failure conditions. Nothing an agent needs in order to call it correctly appears to be missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description still adds real semantics beyond the schema: materialize_path must be absolute, invalid paths fail, overwriting the source frame is forbidden, and max_dimension_px behaves differently under a Guard current-frame hook.

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?

Specific verb + resource (analyze large-form light/dark structure, grayscale evidence) with the audience named (Director value/refinement review). It explicitly distinguishes itself from photoshop_get_preview and photoshop_guard_review_image, so an agent can select it without opening a sibling schema.

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?

Gives an explicit trigger ('when Director value/refinement review needs grayscale evidence') and names two alternatives with the conditions that select them (ordinary color inspection, stored operation review images). It also states the precondition of a pinned document_id and the Guard vs standalone distinction.

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