Skip to main content
Glama
furima-mcp
by fxia0018

check_price

Read-only

Judge whether a listing price is cheap or expensive by comparing it with recent sold prices across Mercari, Yahoo! Auctions and Rakuma, returning a percentile, verdict and sold-price stats.

Instructions

Judge whether a price is cheap or expensive against recent sold prices.

Returns the price's percentile among recent sales (0 = cheaper than every sale, 100 = dearer than every sale), a one-line verdict, and the sold-price statistics.

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": {
      "query": "<query>",
      "price": "<price>"
    },
    "name": "check_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
priceYesThe asking price in JPY to judge.
queryYesSearch keyword, ideally in Japanese.
sitesNoSites with sold history to use. Default: mercari, yahoo, rakuma.
sampleNoSold listings to read per site before filtering.
excludeNoDrop listings whose title contains any of these words (case-insensitive).
max_priceNoMaximum price in JPY.
min_priceNoMinimum price in JPY.
match_all_wordsNoKeep only listings whose title contains every word of the query (ignoring width, case, spaces and hyphens). The sites' own search is fuzzy: 'PS5 CFI-2000' also returns PS5 games.

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 declare readOnlyHint and openWorldHint, so the safety and external-search profile is covered. The description adds useful return-value context — a percentile with the 0/100 scale spelled out, a one-line verdict, and sold-price statistics — which matters since no output schema exists. It does not disclose how the verdict threshold is derived, latency, or that results depend on scraping the named sites.

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

Conciseness5/5

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

Two sentences with zero padding: purpose first, then the return shape with the percentile scale clarified inline. Every clause carries information an agent needs, and nothing is repeated from the schema.

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 tool with no output schema, the description does the necessary work of naming the three returned components and explaining the percentile's direction. It stops short of explaining how the verdict line is computed or what happens when too few sold listings match, which is the main remaining gap for an eight-parameter tool.

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%, with each of the eight parameters already documented (JPY units, sample range, match_all_words rationale, exclusion semantics). The description adds no parameter-level meaning beyond the schema, 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 outcome ('judge whether a price is cheap or expensive') applied to a concrete resource ('recent sold prices'), which distinguishes it from a pure stats sibling like sold_price_stats because it returns a verdict. It does not name any sibling explicitly, so the differentiation is inferred 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?

The phrase 'against recent sold prices' implies this is for evaluating a specific asking price rather than browsing listings, and the required price/query params reinforce that context. However, there is no explicit when-to-use versus sold_price_stats or search_listings, and no stated prerequisites (e.g., network reliance, minimum sample).

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