Skip to main content
Glama

Loyaltie

Search products

search_catalog
Read-onlyIdempotent

Search everyday products from independent brands on Loyaltie. Put the product words from the person's request in catalog.query, a short phrase such as "hot sauce" (every word must match a product, so never a whole sentence); put the rest of their task in context.intent and hard requirements in filters; never add words or narrow beyond what they asked. context is soft (ranks, never removes); filters are hard: price {min,max} in USD cents, ships_from [{country, region}] for the maker's state (e.g. NC), ships_to {country: "US", region} for the US state the order ships to (makers with no state list are kept, including one with no shipping set up; another country returns nothing, which does not rule out delivery there; the cart confirms), categories, shops, occasion, regular_delivery, available (default buyable only). Check messages: a filter that could not be applied is reported there. Amounts are minor units (cents). view "full" adds offers, the Agent Context and all images.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "catalog": "<catalog>"
    },
    "name": "search_catalog"
  }
}

Input Schema

NameRequiredDescriptionDefault
srcNoSend "skill" when you were set up by the Loyaltie Skill; returned links then carry src=skill. Default "api"; any other value counts as "api".
metaNoOptional UCP request metadata. meta["ucp-agent"].profile is your UCP agent profile URL; it is recorded, never required.
catalogYesThe search: query or like, with optional filters, context, pagination and view.
agent_idNoYour agent id. Every loyaltie.com link returned then carries agent=<agent_id>, so Loyaltie knows which agent helped.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), it discloses the critical asymmetry: context is soft and only ranks, filters are hard and remove, and any filter that cannot be applied is reported back in messages. It also explains surprising edge behavior — makers with no state list are kept even with no shipping set up, another country in ships_to returns nothing which does not rule out delivery, and the cart confirms.

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?

Content is dense but nearly every clause carries operational meaning, and the most important instruction (query vs context vs filters) is front-loaded. Structure suffers from a long semicolon-chained paragraph with nested parentheticals that is harder to scan than a short bulleted list would be.

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 deeply nested search tool with an output schema, the description covers the semantics an agent needs to call it correctly: query construction, soft vs hard separation, filter-ignored reporting, and the full view option. Undocumented areas (pagination cursor, src, agent_id, meta) are peripheral and largely self-describing in the schema.

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, but the description adds real meaning: price bounds are inclusive USD cents, ships_from targets the maker's state (e.g. NC), ships_to targets the destination state, available defaults to buyable only, and view "full" expands offers, Agent Context and images. It also frames the query/what-goes-where split that the schema alone leaves ambiguous.

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 everyday products from independent brands on Loyaltie." An agent knows immediately this is a product search tool. It does not explicitly contrast with siblings like lookup_catalog or get_product, so the agent must infer the boundary between keyword search and direct lookup.

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 concrete guidance on how to populate query (short phrase, every word must match, never a whole sentence, only first 8 words count) and how to split the request between context.intent, filters, and query with "never add words or narrow beyond what they asked." Strong context, but no explicit statement of when to prefer a sibling such as lookup_catalog for known-item retrieval.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources