Skip to main content
Glama
amazon-hikaku MCP Server

amazon-hikaku MCP Server

by aegisfleet

search_products

Read-onlyIdempotent

Search product data by keyword, category, brand, price, and recency, and retrieve totals, facets, and refinement suggestions to narrow ambiguous product queries.

Instructions

商品を検索する。query はキーワード(空白区切りでAND)、category は子カテゴリ名・親カテゴリ名・親スラッグのいずれでも可、brand はブランド名またはブランドグループ名(日英表記ゆれは自動で吸収する)。exclude_brand は除外したいブランド名(表記ゆれは同様に吸収する)。exclude_category は除外したいカテゴリ名(子・親・親スラッグのいずれでも可。親を指定すると配下の子カテゴリをすべて除外する)。

sort は score(既定)/ price_asc / price_desc / relevance(タイトル・カテゴリ一致を
重視する関連度順)/ newest(調査日が新しい順)。offset で続きのページを取得できる。
updated_within_days を渡すと、直近その日数以内に調査された商品だけに絞る。

応答には total_count(条件に合う全件数)と facets(全件のブランド・カテゴリ・
親カテゴリ・価格帯)が含まれる。条件が曖昧な相談では、facets の実際の選択肢を
使って絞り込みを提案できる。
結果が3件以下の場合は suggestions(どの条件を緩めると何件出るか)が含まれる。

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_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoscore
brandNo
limitNo
queryNo
offsetNo
categoryNo
max_priceNo
min_priceNo
min_scoreNo
exclude_brandNo
in_stock_onlyNo
exclude_categoryNo
updated_within_daysNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already establish readOnly, idempotent, openWorld and non-destructive, so safety is covered; the description still adds useful behaviour of its own, namely that the response carries total_count, facets and a conditional suggestions block under three results. However, it says nothing about how the default min_score of 80 or the default in_stock_only=true silently filter results, which is exactly the kind of behavioural disclosure that matters for a search tool.

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?

The content is front-loaded into a dense opening block about filters, followed by sort/pagination, then response shape, so an agent can stop reading once it has what it needs. The parenthetical glosses each earn their place, though the text is long enough that trimming the repeated 'いずれでも可' phrasing would help.

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 thirteen-parameter tool with no output schema, the description does the right thing by spelling out the return payload and the conditional suggestions, and annotations handle the safety profile. The gaps are the undocumented price range, limit, min_score and in_stock_only parameters, which leave meaningful filtering behaviour invisible to the caller.

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?

With 0% schema description coverage the description carries the full burden, and it does well on roughly eight of thirteen parameters: AND semantics for query, the child/parent/parent-slug acceptance for category, transliteration tolerance for brand, cascade exclusion for a parent exclude_category, and a full enumeration of sort modes with meaning. But limit, min_price, max_price, min_score and in_stock_only are never mentioned, and those last two have non-obvious defaults that can drop results without explanation.

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?

The opening '商品を検索する' gives a specific verb and resource, and the following sentences sharpen the scope further by defining how query, category, brand and the exclude filters behave. It never names a sibling (e.g. find_similar_products or compare_products) as the alternative path, so the boundary with the other product tools has to be inferred.

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?

The definition gives real workflow guidance: use facets from the response to propose narrowing when a request is vague, and consult suggestions when three or fewer results come back. It also explains what each sort mode is for (relevance weighs title/category matches, newest uses the survey date). What it lacks is an explicit when-not statement or any comparison to sibling tools.

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