Skip to main content
Glama

Pet Welcome Box – hand-picked gift ideas

Search pet welcome kits

search
Read-only

Search pet welcome-kit / first-30-days supplies on an Amazon storefront. Returns search links (results) plus matching hand-picked products with /dp/ links (catalogMatches). marketplace=amazon.com + locale=en-US → English amazon.com results tagged sw-petbox-20; amazon.se → tag sw-petbox-21. marketplace is optional (fallback: country → en-US → amazon.com → else amazon.se).

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoSearch query, e.g. dog crate, no-pull harness (optional; defaults to category keywords)
limitNo
stageNopuppy | kitten | adult | senior
localeNoUser locale, e.g. en-US (US shoppers → amazon.com) or sv-SE (Sweden → amazon.se). If marketplace and country are omitted, en-US selects amazon.com.
countryNoISO country of the shopper, used when marketplace is omitted: US → amazon.com, SE → amazon.se.
speciesNodog | cat | other
sizeBandNotoy | small | medium | large | xl
budgetBandNo
kitCategoryNocontainment | bedding | bowls | cleanup | id-tag | walking | enrichment | grooming
marketplaceNoAmazon storefront: amazon.com (United States — 224 hand-picked products, English, USD, /dp/ links tagged sw-petbox-20) or amazon.se (Sweden, default — 440 products, tag sw-petbox-21); ids us / se also work. Optional: when omitted → country, then locale / Accept-Language en-US → amazon.com, otherwise amazon.se. Other storefronts get search links.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
      +  "description": "ISO country of the shopper, used when marketplace is omitted: US → amazon.com, SE → amazon.se.",
      +  "maxLength": 3,
      +  "minLength": 2,
      +  "type": "string"
      +}
    • changedInput schema / properties / locale / description
      Previous value: -"User locale, e.g. en, sv, de, fr, es"New value: +"User locale, e.g. en-US (US shoppers → amazon.com) or sv-SE (Sweden → amazon.se). If marketplace and country are omitted, en-US selects amazon.com."
    • changedInput schema / properties / marketplace / description
      Previous value: -"Amazon storefront domain or id, e.g. amazon.com, amazon.se, us, se. REQUIRED."New value: +"Amazon storefront: amazon.com (United States — 224 hand-picked products, English, USD, /dp/ links tagged sw-petbox-20) or amazon.se (Sweden, default — 440 products, tag sw-petbox-21); ids us / se also work. Optional: when omitted → country, then locale / Accept-Language en-US → amazon.com, otherwise amazon.se. Other storefronts get search links."
    • changedInput schema / properties / q / description
      Previous value: -"Search query, e.g. dog crate, no-pull harness"New value: +"Search query, e.g. dog crate, no-pull harness (optional; defaults to category keywords)"
    • removedInput schema / properties / q / minLength
      Removed value: -1
    • removedInput schema / required
      Removed value: -[
      -  "q",
      -  "marketplace",
      -  "locale"
      -]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds real behavioral context beyond that: what is returned (search links plus hand-picked /dp/ matches), which affiliate tag applies per storefront, and that other storefronts degrade to search links only. Return format is described without an output schema, which is valuable.

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?

Three tight sentences, front-loaded with the core action and outputs, with the fallback logic last. The arrow notation and tag strings are dense but readable; nothing is obviously wasted.

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?

Ten optional parameters with no output schema make this a moderately complex tool, and the description compensates by explaining both return structures and the defaulting behavior when marketplace/country/locale are omitted. It stops short of describing result limits or ranking behavior, but an agent has enough to call it correctly.

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 80%, so the baseline is 3. The description restates the marketplace/country/locale precedence chain that individual parameter descriptions already cover, adding a consolidated view but little new meaning. Parameter-specific detail such as limit bounds or query defaults is left entirely to the schema.

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 pet welcome-kit / first-30-days supplies on an Amazon storefront. It also names the two outputs (search links and catalogMatches), so the agent knows what it retrieves. It does not distinguish itself from siblings like resolve_product, but the purpose itself is unambiguous.

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 explains the marketplace fallback chain and that marketplace is optional, which is useful operational guidance. It never says when to call this versus resolve_product or list_marketplaces, nor when a direct product lookup is preferable to a query search, so routing guidance is only implied.

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