Skip to main content
Glama
lavalava45

PaintPilot

by lavalava45
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

photoshop_guard_set_art_run

Create or update durable art-run settings bound to a verified Photoshop document and immutable process directory, probing readiness and persisting Guard configuration without painting. Retrieve existing runs instead of re-registering.

Instructions

Create or update durable art-run settings for a verified document; use photoshop_guard_resume to retrieve an existing run rather than registering it again. Requires document_id and process_dir; bind document and immutable process_dir, and preserve the original user request verbatim as original_brief, never a success summary. Probes Photoshop/UXP readiness and document identity, creates the process directory and persists Guard settings without painting. Honor presentation_context.painting_profile_selection from the Photoshop panel for NEW art runs; auto allows an explicit choice based on the brief and defaults to nontrivial_painting if omitted. Existing profile locks and transition gates remain enforced. Brush preflight is required before dependent brush operations; supply observed evidence or the brush_pack_profile preflight, not invented preset claims. Commentary settings control presentation, not execution permission. Returns ok, art_run, capability context and next guidance; invalid identity/path/profile/preflight returns isError=true with guard_art_run_rejected and message. Changing original_brief invalidates its evaluation binding; settings alone do not prove painting completion.

Input Schema

NameRequiredDescriptionDefault
document_idYesPositive Photoshop document id for the verified live document whose art-run settings are bound; never substitute another tab to bypass identity checks.
process_dirYesRepository-relative path exactly processes/<subject>-process/<run-name> using lowercase kebab-case.
original_briefNoOriginal user request for independent evaluation; changing it invalidates the evaluation binding, so never substitute a success summary.
brush_preflightNoDurable live brush-role map recorded after bounded installed-preset inventory, effective-settings readback and any role-critical footprint probes.
commentary_modeNoPresentation style: technical audit text, artistic commentary or mixed. Omission retains existing/user settings; this does not authorize or block painting.mixed
painting_profileNoHonor the Photoshop panel profile for a new run: simple_graphic or nontrivial_painting. If the panel says auto, select according to the brief; omission defaults to nontrivial_painting. Existing runs keep their profile/Guard transition rules.nontrivial_painting
brush_pack_policyNoOptional supplied-pack execution policy. preferred allows justified fallback; exclusive means every brush/stamp mark must be explicitly bound to this evidence-backed pack while non-brush Photoshop operations remain available.
commentary_detailNoshort: intent/tools/observation; normal adds layer/preset/settings; detailed adds colors/opacities/gradient stops; technical keeps audit text; no translation.normal
profile_transition_reasonNoOptional reason for upgrading simple_graphic; the stronger profile requirements still apply.
brush_preflight_invalidationNoOptional explicit invalidation for a replacement brush preflight. Catalog/settings drift is inferred from newly observed inventory/preset/settings evidence when unambiguous; runtime_changed remains explicit when host/runtime evidence requires a reprobe.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.8.3
    • addedInput schema / properties / commentary_mode / description
      Added value: +"Presentation style: technical audit text, artistic commentary or mixed. Omission retains existing/user settings; this does not authorize or block painting."
    • addedInput schema / properties / document_id / description
      Added value: +"Positive Photoshop document id for the verified live document whose art-run settings are bound; never substitute another tab to bypass identity checks."
  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?

With no annotations, the description carries the full behavioral burden and does: it discloses side effects (creates the process directory, persists Guard settings), states it does NOT paint, notes readiness/identity probes, warns that changing original_brief invalidates the evaluation binding, clarifies commentary settings do not grant execution permission, and documents the isError/guard_art_run_rejected failure mode.

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?

Purpose is front-loaded in the first clause and essentially every sentence carries operational content with no filler. However, it is a single dense block of run-on clauses mixing routing, parameter rules, preflight rules, and return shape, which makes it harder to scan than a shorter, segmented version would be.

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?

Despite 10 parameters, deep nesting and no output schema, the description still explains the return payload (ok, art_run, capability context, next guidance) and the error contract, plus invalidation and non-authorization limits. Nothing an agent needs to invoke it correctly is 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 the baseline is 3; the description adds real semantics beyond the schema — original_brief must be the verbatim user request and never a success summary, document_id is an identity binding that cannot be swapped for another tab, and commentary_mode governs presentation only. It stops short of explaining nested brush_preflight/brush_pack_policy fields, which the schema covers.

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?

States a specific verb pair and resource ("Create or update durable art-run settings") scoped to "a verified document," and explicitly distinguishes itself from photoshop_guard_resume for retrieval of an existing run. An agent can pick between the two without opening either 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?

Names the alternative ("use photoshop_guard_resume to retrieve an existing run rather than registering it again") and states the selecting condition. It also spells out conditional rules for painting_profile (honor the panel value for NEW runs; auto resolves from brief; omission defaults to nontrivial_painting) and when brush preflight is mandatory.

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