Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

list_cached_designs

Read-only

List locally cached 3D designs, newest first, with optional material filtering and a result limit, so agents can find reusable models before regenerating them.

Instructions

List cached designs, optionally filtered by material.

        Args:
            material: Filter by material (e.g. "PLA", "PETG").
            limit: Maximum number of results.

        Most recently used designs come first.

        The response declares its ``scope``: which store was read.
        The cache is local-only at every tier (regenerable files,
        no cloud copy), so a complete local read is the whole
        cache.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_cached_designs"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of results. Default: 50.
materialNoFilter by material (e.g. "PLA", "PETG").

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.5.1
    • changedInput schema / properties / limit / description
      Previous value: -"Default: 50."New value: +"Maximum number of results. Default: 50."
    • addedInput schema / properties / material / description
      Added value: +"Filter by material (e.g. \"PLA\", \"PETG\")."
  2. Changed3 schema fields changedv1.5.0
    • removedInput schema / properties / limit / default
      Removed value: -50
    • addedInput schema / properties / limit / description
      Added value: +"Default: 50."
    • removedInput schema / properties / material / default
      Removed value: -null
  3. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that: deterministic ordering ('most recently used designs come first'), the fact that the response declares a `scope` field, and the local-only/regenerable nature of the cache which implies no auth or remote dependency. It could go further on what happens with a non-matching material filter, but the disclosure is substantive.

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?

It is front-loaded with the action and filter, then ordering, then the response/cache semantics — a sensible order with no filler. The Args block duplicates the schema verbatim, which is mild redundancy, and the scope/local-only explanation spans three lines for one idea.

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 two-optional-parameter read tool with no output schema, the description supplies what is missing from structured data: result ordering and the presence of a `scope` field in the response. Remaining gaps (total count, what an empty result means, whether limit defaults are applied) are minor given the stated local-only completeness.

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 coverage is 100%, and both parameters are documented in the schema itself (limit with 'Default: 50', material with PLA/PETG examples). The description merely restates the same material example and adds no new meaning such as case-sensitivity, partial matching, or behaviour for unknown materials, so the baseline 3 applies.

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 first sentence gives a specific verb and resource ('List cached designs') plus an optional filter, which is unambiguous. It does not name any sibling (e.g. get_cached_design, search_cached_models, list_cached_models) to distinguish itself from the large family of cache-related tools, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'optionally filtered by material' and the statement that a complete local read is the whole cache, which tells the agent it need not paginate or worry about cloud data. There is no explicit when-to-use / when-not-to-use guidance and no mention of the alternative tools for retrieving a single design or searching the cache.

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