Skip to main content
Glama
Sign In

Wunderlust

by xyz.wunderlust
OverviewDiscussionsAdmin

Search cards

search_references
Read-onlyIdempotent

Search Wunderlust, a hand-picked collection of creative inspiration: award-winning sites, motion and 3D/WebGL libraries, UI components, inspiration galleries, AI image/video/voice tools, AI agents and Claude Code skills. Takes a free-text query in English or Portuguese (e.g. "scroll storytelling", "animação de texto") and/or filters by category, tags or editorial pick. Returns a ranked list of cards: name, id, category, tags, short description, a "steal" field (the one idea worth exploring in it), official link and Wunderlust page. The ids in the list work with get_references for the full write-up. Provide at least one of query, category, tags, pattern or pick.

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": "search_references"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the returned text: "en" (default) or "pt".
pickNoOnly cards in this editorial selection.
tagsNoOnly cards that have ALL of these tags (e.g. free, open-source).
limitNoMaximum number of results (1-25).
queryNoFree-text search, English or Portuguese. Describe what you need.
patternNoOnly cards tagged with this pattern: a recurring idea worth exploring (e.g. kinetic-type, hover-fx, classical-art). See list_facets.
categoryNoOnly cards in this category.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / category / description
      Previous value: -"Only references in this category."New value: +"Only cards in this category."
    • changedInput schema / properties / pattern / description
      Previous value: -"Only references tagged with this pattern: a recurring idea worth exploring (e.g. kinetic-type, hover-fx, classical-art). See list_facets."New value: +"Only cards tagged with this pattern: a recurring idea worth exploring (e.g. kinetic-type, hover-fx, classical-art). See list_facets."
    • changedInput schema / properties / pick / description
      Previous value: -"Only references in this editorial selection."New value: +"Only cards in this editorial selection."
    • changedInput schema / properties / tags / description
      Previous value: -"Only references that have ALL of these tags (e.g. free, open-source)."New value: +"Only cards that have ALL of these tags (e.g. free, open-source)."
  2. Changed1 schema field changed
    • changedInput schema / properties / pattern / description
      Previous value: -"Only references tagged with this pattern: a recurring idea worth stealing (e.g. kinetic-type, hover-fx, classical-art). See list_facets."New value: +"Only references tagged with this pattern: a recurring idea worth exploring (e.g. kinetic-type, hover-fx, classical-art). See list_facets."
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-redundant behavior: the ranked-list return shape and its fields (including the 'steal' field), bilingual query support, and the requirement of at least one filter — details an agent cannot get from the annotations or schema.

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?

Dense but mostly load-bearing, with the return shape and the minimum-filter rule front-loaded toward the end of a single paragraph. The opening enumeration of content types (award-winning sites, 3D/WebGL, AI tools, etc.) largely restates the category enum and could be trimmed.

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 7-parameter, zero-required discovery tool with no output schema, the description supplies the return fields, the id-to-get_references continuation path, and the at-least-one-filter rule. Nothing material is missing for an agent to invoke it correctly.

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, and the description goes beyond it: it explains that query is free-text in English or Portuguese with worked examples, that tags combine conjunctively via the schema, and that query/category/tags/pattern/pick are the filter set with an at-least-one constraint. It does not explain the interaction between query language and the lang parameter.

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 (search) over a specific resource (Wunderlust cards), enumerates the content domains covered, and distinguishes itself from get_references by naming the id handoff. An agent can tell instantly this is the discovery/query entry point.

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

Usage Guidelines4/5

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

Gives a concrete selection rule ('Provide at least one of query, category, tags, pattern or pick') and routes to get_references for the full write-up. It does not contrast with the other siblings (random_references, similar_references, show_references, list_facets), so an agent still has to infer when serendipity or similarity is the better call.

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

All Wunderlust toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources