Skip to main content
Glama

iterate_decoration

Create a new version of a saved decoration, archiving the current one (Kiln Pro).

Instructions

Create a new version of a saved decoration, archiving the current one (Kiln Pro).

        Use this when tuning a decoration -- a new depth, mode, style or
        content file -- and the previous version stays available for
        ``rollback_decoration``.

        :param name: Decoration name or slug.
        :param content_path: New content file (empty = keep current).
        :param depth_mm: New depth in mm (0 = keep current).
        :param mode: New mode (empty = keep current).
        :param image_style: New image style (empty = keep current).
        :param notes: Free-text notes for this iteration.
        :returns: Dict with the new version and what changed.
        

Input Schema

NameRequiredDescriptionDefault
modeNoDefault: "".
nameYes
notesNoDefault: "".
depth_mmNoDefault: 0.0.
image_styleNoDefault: "".
content_pathNoDefault: "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does well: it discloses that the current version is archived (not overwritten), that the old version is recoverable, and that the feature is Kiln Pro-gated. It stops short of permissions, validation failures, or whether repeated calls stack versions, which are the remaining mutation-risk details.

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 with what happens (new version + archive) before the usage guidance, which is the right ordering. The Sphinx :param:/:returns: block is slightly repetitive with the schema titles but still reads compactly; nothing is wasted.

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 6-parameter mutation with no output schema, the description covers the side effect, the recovery path, the license gate, and the return shape ("dict with the new version and what changed"). Only failure/validation behavior is unaddressed, which is a minor gap at this complexity.

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

Parameters5/5

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

Schema coverage is already 83%, but the description adds the critical semantics the schema omits: empty string or 0 means "keep current," which changes how an agent constructs the call rather than just labeling fields. It also clarifies name accepts a name or slug and that notes are free-text for this iteration.

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: creates a new version of a saved decoration and archives the current one. It also names rollback_decoration as the counterpart path, so an agent can separate it from sibling mutation tools like save_decoration or apply_decoration without opening the 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?

"Use this when tuning a decoration -- a new depth, mode, style or content file" gives an explicit trigger condition, and it states that the prior version remains reachable via rollback_decoration, which is the key alternative an agent would otherwise confuse it with.

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