Skip to main content
Glama

kalicart-global

by io.github.giuseppesocci-bot

global_search

Read-onlyIdempotent

Search the KaliCart Global federated index: real product offers across independent WooCommerce merchants that opted in via the ARC (Agent-Readable Catalog) protocol. Returns merchant-authoritative prices, UCP availability_status, storefront URLs and canonical category leaves. Provide q (free text) and/or leaf (canonical category). Spec: https://bridge.kalicart.com/spec/

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFree-text product query. Each term must match as a whole word in the native merchant catalog text (name, short description, description) or in the canonical category path, so English category terms reach catalogs written in other languages: q="mattress" returns products under home.bedroom.mattress even when their text is Italian. There is no server-side translation of product text; for language-neutral retrieval by category use leaf and the canonical filters.
leafNoCanonical category node. Accepts a terminal leaf (e.g. beverages.alcohol.sparkling_prosecco) or any parent node (e.g. jewellery, home.bedroom): a parent matches the node and its whole subtree, so you can widen or narrow the search by moving up or down the tree. Use list_categories to browse the tree.
brandNoBrand facet filter (normalized, e.g. "nike")
colorNoColor family (e.g. "blue")
limitNoMax offers to return (1-25, default 10). No pagination; raise to get more in one call
genderNoGender facet (normalized): male, female, unisex, kids
in_stockNoOnly offers with availability_status=in_stock
max_priceNoMaximum price filter (numeric; per-offer merchant currency, no FX conversion)
min_priceNoMinimum price filter (numeric; per-offer merchant currency, no FX conversion)

TDQS

A4/5.0
Behavior4/5

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

Annotations already indicate read-only, idempotent, and open-world behavior. The description adds context by noting that the index includes only merchants who opted in via ARC, and that returned data is merchant-authoritative. It does not contradict annotations and provides useful behavioral detail.

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 description is concise and front-loaded, stating the core purpose in the first sentence. It uses 2-3 sentences total, includes a spec link, and avoids wasted words.

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?

Despite having no output schema, the description lists key returned fields (prices, availability, storefront URLs, category leaves) and explains the overall context. The spec link serves as a fallback. It covers the essential information for a complex federated search tool, though a full output schema would be beneficial.

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?

The input schema covers all 9 parameters with rich descriptions (100% coverage), so the schema does the heavy lifting. The description's mention of q and leaf is redundant and does not add additional meaning beyond what the schema already provides. No param-specific nuance is added.

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?

The description clearly identifies a specific action: 'Search the KaliCart Global federated index' and explains what it returns (offers, prices, availability, storefront URLs, categories). It distinguishes itself from sibling tools like get_product and list_categories by its global, cross-merchant scope.

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?

The description provides usage instructions for parameters ('Provide q and/or leaf') but does not explicitly state when to use this tool versus alternatives such as get_product or list_merchants. The federated context implies broad search usage, but no exclusions or alternative tool recommendations are given.

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

All kalicart-global toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Each tool has a clear, distinct purpose: product detail retrieval, global search, category listing, merchant listing, and merchant ARC verification. No two tools overlap in function.

Naming Consistency4/5

Most tools follow a verb_noun pattern (get_product, list_categories, list_merchants, lookup_merchant), but 'global_search' deviates from that pattern by leading with an adjective rather than a verb. Scores are minor and readability remains high.

Tool Count5/5

With 5 tools, the server is well-scoped for a federated commerce search catalog. Each tool earns its place without redundancy or bloat.

Completeness5/5

The surface covers the essential workflows: searching for products, retrieving product details, discovering categories and merchants, and verifying a merchant's ARC compliance. No obvious gaps for the stated purpose.

Resources