Skip to main content
Glama

Valentine's Day Gifts – hand-picked gift ideas

One-shot create and fill

create_and_fill

One call: create a curated Valentine's Day (Alla hjärtans dag) gift wishlist and return shopUrl (share link) + ownerUrl. Preferred agent path: create a Valentine wishlist and add ASINs / keywords / search queries in one call. Returns id, editToken, ownerUrl, shopUrl. Use recipientName, occasion, categories (not childName/ageBand). OpenAPI: agentCreateAndFill.

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": "create_and_fill"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoUser locale, e.g. en-US, en, sv. amazon.com always answers in English.
countryNoISO country of the shopper, e.g. US or SE. Used when marketplace is omitted (US → amazon.com).
occasionNo
itemAsinsNo
styleTagsNo
budgetBandNo
categoriesNo
itemQueriesNoEach query is searched and added as a wish
marketplaceNoAmazon storefront for the end user: amazon.com (United States) or amazon.se (Sweden, default); ids like us/se also work. Pass marketplace=amazon.com for US shoppers to get amazon.com/dp/ASIN links with English titles. If omitted, country is used, then Accept-Language (en-US → amazon.com), else amazon.se. A missing store never errors.
itemKeywordsNo
relationshipNo
recipientNameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
      +  "description": "ISO country of the shopper, e.g. US or SE. Used when marketplace is omitted (US → amazon.com).",
      +  "type": "string"
      +}
    • addedInput schema / properties / locale
      Added value: +{
      +  "description": "User locale, e.g. en-US, en, sv. amazon.com always answers in English.",
      +  "type": "string"
      +}
    • addedInput schema / properties / marketplace
      Added value: +{
      +  "description": "Amazon storefront for the end user: amazon.com (United States) or amazon.se (Sweden, default); ids like us/se also work. Pass marketplace=amazon.com for US shoppers to get amazon.com/dp/ASIN links with English titles. If omitted, country is used, then Accept-Language (en-US → amazon.com), else amazon.se. A missing store never errors.",
      +  "type": "string"
      +}
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

With readOnlyHint=false and openWorldHint=true already declared, the description's main added value is disclosing the returned fields (id, editToken, ownerUrl, shopUrl) — useful, since editToken is a sensitive write credential and no output schema exists. It says nothing about side effects, idempotency, auth needs, or rate limits for what is a mutating, open-world call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and return values, which is good. But the return contract is stated twice ('shopUrl (share link) + ownerUrl' then 'Returns id, editToken, ownerUrl, shopUrl') in slightly inconsistent form, and the childName/ageBand clause spends words on guidance that does not apply to this schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, zero-required mutation with no output schema, the description covers the core action, one-shot rationale, and return fields. It omits what happens with no items supplied, whether repeated calls create duplicates, and the semantics of half the inputs, though marketplace resolution is well handled by the schema itself.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% across 12 parameters, so the description must compensate, and it only names recipientName, occasion, categories and loosely maps ASINs/keywords/search queries to itemAsins/itemKeywords/itemQueries. It leaves styleTags, budgetBand, relationship, locale and country entirely unexplained, and the instruction to use 'recipientName, occasion, categories (not childName/ageBand)' references non-existent parameters, which actively confuses the mapping (additionalProperties is false).

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+resource (create and fill a Valentine's Day gift wishlist) and its payoff (shopUrl share link + ownerUrl). The line 'Preferred agent path: create a Valentine wishlist and add ASINs / keywords / search queries in one call' implicitly distinguishes it from the create_wishlist + add_wishlist_item pair, but it never names those siblings explicitly, so the differentiation is inferential rather than stated.

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?

'Preferred agent path' signals this is the default one-shot route versus a multi-step alternative, which is genuine usage guidance. However, the guidance 'Use recipientName, occasion, categories (not childName/ageBand)' references parameters that do not exist in the schema and gives no explicit when-not conditions, leaving the agent to infer the create_wishlist alternative.

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