Skip to main content
Glama

manage_design_style

Manage saved Design Styles and the current project's visual identity. For concrete MG instances, use browse_library.

When the user asks to select/use a Design Style for the project, saving that selection is required before applying its linked caption or scene templates: call apply with designStyleId for a saved style, or apply_preset with presetId for a catalog style. Then call get WITHOUT designStyleId and verify the active style ID matches. Reading get with an ID, applying a caption preset, or copying a scene template does not save the project's Design Style. Do not report a style as selected until the active-style readback confirms it. For comparison, preview, or plan-only requests, get remains read-only: do not apply a style unless the user requested selection.

For caption recommendations or edits, call action="get" to read the active style on demand. It returns captionTemplates.preferredTemplateId/preferredPreset and captionTemplateDetails (names, availability, supported languages, fonts), plus application instructions. Read caption readiness with read_captions before applying. A style preference changes neither captions nor their language by itself. Plan-only requests must not edit or transcribe.

Actions: list saved/active styles; get full spec and caption/scene details (or inspect designStyleId); create a custom identity (auto-applies unless applyToProject:false); apply a saved ID; update spec/name/cover; clear the project selection; delete a saved style. Catalog edits fork a user copy. No active style is normal.

list_presets returns picker summaries (collages and catalog UUIDs), not the full designSpec. Filter with applicableLanguages/scenario/query; locale only localizes labels. Follow nextBrowse within scope. apply_preset selects the catalog UUID without copying it.

On confirmation_required, relay impact and ask before retrying: confirmShared:true for shared updates; confirm:true for deletion. Assets survive deletion. See designSpec/patch parameter docs for shapes and merge rules.

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": {
      "action": "<action>"
    },
    "name": "manage_design_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoFor create (required): name for the new design style. Unique per user; server deduplicates with suffix if needed.
limitNo
patchNoFor update: JSON string of a partial DesignSpec (same shape as designSpec); may be combined with rename. Colors merge by palette + role when palette is given; without palette a role must identify one color. Fonts with language merge by language + role, otherwise by role/family. fontRecommendations (the reviewed en / zh-Hans pools that get returns) replaces the pool and never replaces default fonts. logos, images, and referenceSources REPLACE their arrays: get first and include entries to keep. styleGuide replaces; an empty string clears it.
queryNo
actionYesSupported actions: list, get, create, update, apply, clear, delete, list_presets, apply_preset.
localeNoFor list_presets (optional): user's chat language code ('en', 'zh', 'zh-hant', 'es', or 'ja'). Catalog preset names/descriptions are stored with English canonical + locale overrides; passing the user's language returns localized text. Defaults to English if omitted.
offsetNo
renameNoFor update: new name to rename the design style to. Can be combined with `patch` in the same call.
confirmNoFor delete only: set to true ONLY after the user has confirmed the deletion. Omit on first call to trigger the confirmation_required protocol.
presetIdNoFor apply_preset (required): the catalog UUID returned by list_presets. The backend pins the project's designStyleId FK directly at this catalog row — no clone is made until the user actually edits the spec.
scenarioNoFor list_presets (optional): scenario tag to narrow the catalog by. Catalogs tag themselves with applicableScenarios for recommendation / selection; omit to list all visible catalog presets.
designSpecNoFor create: JSON string of a DesignSpec. Each array element's role names its use (primary, heading, wordmark…). Shape: {"colors":[{"role":"primary","value":"#6C5CE7"}],"fonts":[{"role":"heading","family":"Inter","language":"en","weight":700,"style":"normal"}],"logos":[{"role":"wordmark","url":"https://..."}],"images":[{"role":"style reference","url":"https://..."}],"referenceSources":[{"id":"mg-reference:style:<UUID>"}],"styleGuide":"Editorial typography; heading weight 700."}. colors: hex value + usage role, optional palette label. fonts: CSS family + role; optional language, numeric weight, style, sourceUrl, and review evidence (match, validation, notes); keep preset defaults. logos/images: url + role; only images listed here guide generation (thumbnailUrl and referenceSources do not). referenceSources: style or instance IDs recording visual-identity sources; one-off form sources belong to individual MG calls. styleGuide: reusable confirmed tone, material, motion, and typography rules not captured by fonts, without repeating the palette or inventing one-off layouts.
thumbnailUrlNoFor create / update: optional UI cover image URL for the Design Style library / picker. This is not part of designSpec and is not used as a generation reference. Pass null on update to clear it.
confirmSharedNoFor update only: set to true after the user has confirmed it's OK to edit a design style used by multiple projects. Omit on first call so the confirmation_required response can surface the impact.
designStyleIdNoUUID or the short ID from list / list_presets. For get / update (optional — defaults to the targeted project's applied design style, so required when no project is targeted) or for apply / delete (required).
applyToProjectNoFor create / apply_preset: whether to apply the style to the targeted project (default true). With no targeted project, create saves to the library only.
applicableLanguagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations, it discloses auto-apply on create (unless applyToProject:false), fork-on-edit for catalog styles, that catalog apply_preset pins an FK without cloning, that assets survive deletion, that no active style is a normal state, and the confirmShared/confirm confirmation gates. Mild tension exists between destructiveHint=false and the advertised delete action, but deletion is scoped to a user-created style and is gated by an explicit confirmation step.

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

Conciseness3/5

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

The purpose is front-loaded, but the text is long and packs procedural workflow, per-action rules, and parameter caveats into the same paragraphs as the overview. Several sentences restate constraints already stated in the schema (e.g. confirmShared, confirm, applyToProject), so not every sentence earns its place.

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

Completeness4/5

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

For a 17-parameter, nine-action tool with no output schema, the description covers the return content of get (captionTemplates fields and details), list_presets (picker summaries, nextBrowse), and the readback verification contract. Gaps remain around what list and create return and how offset/limit paging behaves, which the agent must infer.

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?

With 76% schema coverage the schema already carries most field meaning, yet the description adds real semantics: get without designStyleId reads the active style, locale only localizes labels while applicableLanguages/scenario/query do the filtering, list_presets returns summaries rather than full designSpec, and designSpec/patch shapes and merge rules are pointed to rather than duplicated.

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

Purpose4/5

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

The description names the resource (saved Design Styles and the project's visual identity) and enumerates the nine actions, and it explicitly routes concrete MG instance lookups to browse_library. It is specific about what the tool owns, though the dense multi-paragraph layout makes the core purpose slower to extract than a one-line scope statement would.

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 states when to use apply vs apply_preset vs get, describes the required readback verification before reporting a style as selected, and warns that get with an ID or applying a caption preset does not save the selection. It also carves out the when-not case ('For comparison, preview, or plan-only requests... do not apply a style unless the user requested selection') and explains the confirmation_required retry protocol.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.