Skip to main content
Glama

photoshop_recipe_remove_distraction

Destructive

Remove selected distractions from a Photoshop document using generative AI or content-aware fill, all in one undoable step.

Instructions

One-shot distraction removal: generative AI remove when available, else content-aware fill. Wrapped in a single undoable history step.

Users often say: remove that person, erase distraction, content aware remove, clone out object.

Use when: the user has selected the object or region to remove. Do NOT use when: no selection exists — use photoshop_select_rectangle or photoshop_select_subject first.

Returns: { ok, summary, undo_history_states_consumed, details }. Preconditions: active document with an active pixel selection. Side effects: fills/removes selected pixels; clears selection.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
feather_pxNoEdge feather in pixels before remove (0-20, default 0)
document_idYesPhotoshop document id from photoshop_get_state / photoshop_list_documents. Send null or 0 to use the active document. A positive number activates that document before the tool runs. When no document is open, a stale id does not block the call.
use_generativeNoPrefer generative remove when Photoshop supports it (default true when capable)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.7.33
    • changedInput schema / properties / document_id / description
      Previous value: -"Photoshop document id from photoshop_get_state / photoshop_list_documents. Send null to use the active document. A number activates that document before the tool runs."New value: +"Photoshop document id from photoshop_get_state / photoshop_list_documents. Send null or 0 to use the active document. A positive number activates that document before the tool runs. When no document is open, a stale id does not block the call."
  2. Changed4 schema fields changedv1.7.32
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / document_id / description
      Previous value: -"Optional Photoshop document id from photoshop_get_state / photoshop_list_documents. When set, the tool activates that document before running so a UI tab switch cannot retarget the edit."New value: +"Photoshop document id from photoshop_get_state / photoshop_list_documents. Send null to use the active document. A number activates that document before the tool runs."
    • changedInput schema / properties / document_id / type
      Previous value: -"number"New value: +[
      +  "number",
      +  "null"
      +]
    • addedInput schema / required
      Added value: +[
      +  "document_id"
      +]
  3. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds context annotations can't: that the whole operation collapses into a single undoable history step, the precondition of an active pixel selection, and the concrete side effect that selected pixels are filled/removed and the selection is cleared.

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

Conciseness5/5

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

The core behavior and mechanism lead the description, followed by labeled trigger phrases, when/when-not rules, return shape, preconditions, and side effects. Every section is short and earns its place with no filler.

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?

For a destructive recipe tool with no output schema, the description covers everything an agent needs: mechanism, return shape, preconditions, and side effects. The absence of an output schema is compensated by the explicit 'Returns: { ok, summary, undo_history_states_consumed, details }' line.

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 all three parameters (feather_px, document_id, use_generative) are already fully documented in the schema. The description's 'generative AI remove when available' loosely maps to use_generative but adds no format, range, or default detail beyond what the schema provides, so the baseline of 3 applies.

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?

It states a specific verb+resource (distraction removal) and describes the mechanism precisely: generative remove when available, otherwise content-aware fill, as one undoable step. This clearly differentiates the wrapper recipe from sibling primitives like photoshop_generative_remove and photoshop_content_aware_fill, which do only one of the two paths.

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 gives explicit 'Use when' (user has selected the object) and 'Do NOT use when' (no selection) rules, and names the exact alternatives to reach for instead (photoshop_select_rectangle or photoshop_select_subject). Nothing about tool selection is left to inference.

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