Foldsquare

Search products

search_products

Read-only

Search the merchant's products. For a connected store (Shopify, WooCommerce, BigCommerce, Ecwid, Wix) this queries the store live; otherwise it reads products stored in Foldsquare. The ids it returns are exactly what create_catalog takes as products: { from: "ids", ids: [...] }. Not every store can apply every filter, and a filtered search may stop before it has looked at everything — then partial is true and note says what was covered: the result is not the complete set.

Input Schema

Name	Required	Description	Default
`sort`	No	Default "relevance", which on most stores means the store's own order; "title" gives a predictable alphabetical order. `coverage.sortApplied` reports what was actually used.
`tags`	No	Keep only products carrying these tags. Not every store exposes tags — same reporting as productType.
`limit`	No	How many products to return (default 20). A page size, not a total — use `cursor` for the rest.
`order`	No	Direction for `sort`.
`cursor`	No	Continues a previous search: `nextCursor`, with EVERY OTHER ARGUMENT UNCHANGED. A cursor sent with changed filters is refused.
`search`	No	Free-text match on title and SKU. On a connected store this is the store's own search, so what counts as a match varies by platform; `coverage` says who did the matching.
`source`	No	Where to read. "auto" (default) queries the connected store if there is one. Use "foldsquare" to find products added with import_products: those are not in the store, so "auto" will never return them.
`status`	No	Publication status, default active, which leaves drafts out; "any" includes them.	active
`vendor`	No	Keep only these vendors/brands. Exact match, case-insensitive; any one counts. Call list_product_facets first to get the real spellings instead of guessing at them.
`tagsMode`	No	"any" (default) keeps a product carrying at least one of the tags; "all" requires every one.
`productType`	No	Keep only these product types. Several platforms have no such field; there the filter is reported under `coverage.unsupported` rather than quietly matching nothing.
`availability`	No	Purchasability, NOT inventory count: a made-to-order product with zero on hand is in stock. This is what a merchant means by "in stock". Default "any".
`collectionId`	No	Restrict to one collection/category. Take the id from list_collections — a collection NAME will not work on a connected store.

Output Schema

Name	Required	Description
`note`	No
`total`	Yes	null when the store does not say
`source`	Yes	Where the products were read: the store platform or foldsquare
`hasMore`	Yes
`partial`	Yes	true: the search stopped before covering everything; `note` says what was covered
`coverage`	Yes	Which filters the store applied, and how far the search looked
`products`	Yes
`returned`	Yes
`nextCursor`	Yes	Pass as `cursor`, with every other argument unchanged, for the next page
`totalIsExact`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already cover the read-only, non-destructive, closed-world profile, and the description adds real value beyond them: live vs stored reads, that some stores cannot apply every filter, and that filtered searches can stop early with `partial` and a `note` explaining coverage. It does not discuss rate limits or cost, but the partial-result warning is the important behavioral disclosure.

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?

Four sentences with no filler, front-loading the resource and backend distinction before the output-contract and partial-result caveat. Dense but each sentence carries information an agent needs.

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 13-parameter search tool with an output schema and full schema descriptions, the description supplies the pieces the schema cannot: which backend is read, the id contract with create_catalog, and the meaning of `partial`/`note`. Complete enough to call correctly without opening the schema.

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 description coverage is 100%, so the parameters are already fully documented. The description adds only a general caveat that filters may be unsupported per store; it provides no per-parameter guidance beyond what the schema states, 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?

States a specific verb and resource ("Search the merchant's products") and immediately clarifies the two backends it can hit: a live connected store or Foldsquare-stored products. It does not explicitly distinguish itself from near-name siblings like pick_products_search or get_product, 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 Guidelines4/5

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

Gives a concrete usage rule: connected store → live query, otherwise Foldsquare, and notes that import_products additions are only visible via the Foldsquare source. It omits when an agent should prefer a different search/pick tool, so alternatives are only partially addressed.

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

All Foldsquare tools Inspect

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

Need Help?