Skip to main content
Glama

入札案件観測所

落札結果を探す・数える

search_awards
Read-onlyIdempotent

Use this when the user asks who won, or how often, in Japanese public procurement: award and contract results from 2004 onward for national agencies and local governments. Filter by keyword, buyer, supplier, area, category and period; set group_by to get counts instead of rows. At least one of keyword, buyer, supplier or a non-default status is required. Counts include only results that reached an award or contract; unsuccessful (不調), cancelled (中止) and unresolved (結果未確定) records are counted separately in not_awarded, or listed with status. Amounts are shown as bands. 落札結果・契約結果・落札者・随意契約

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_awards"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoPrefecture of the buyer. Accepts 福岡県, 福岡, Fukuoka, 40 (JIS code), national (国の機関)
buyerNoProcuring entity: name, abbreviation (国交省) or buyer_id
limitNoRows per page, 1-10 (default 10)
cursorNonext_cursor from the previous result, with the same other arguments. Up to 3 pages.
statusNoawarded (default): only results that reached an award or contract (落札・契約). unsuccessful = 不調 (no valid bid), cancelled = 中止, unresolved = 結果未確定 (published without a winner), not_awarded = those three together, all = every record. Counts and rankings use only awarded results unless you set this.
date_toNoResult date on or before, YYYY-MM-DD
keywordNoWords in the contract title. Space = AND. Example: 庁舎 清掃
categoryNo物品=goods/supplies, 工事=construction works, 役務=services/outsourcing (業務委託), 保守=maintenance, 設計・調査=design/survey/consulting, IT=systems/software/IT equipment, 賃貸借=lease/rental, イベント=events, その他=other
group_byNonone (default): rows, newest first. Otherwise counts per group: all years, the top 10 buyers/suppliers/categories, or all amount bands (amount_band: number of records in each published-amount band, plus records without an amount).
supplierNoWinning company: name as the user wrote it, 13-digit corporate number (法人番号) or supplier_id. A name matching several companies returns candidates
date_fromNoResult date on or after, YYYY-MM-DD
fiscal_yearNoJapanese fiscal year (April to March). 2024 = 2024-04-01 to 2025-03-31 = 令和6年度. 令和N年度 = 2018+N.
response_formatNoconcise (default): fewer fields per row. detailed: adds IDs, method, original URL and retrieval date per row.

Output Schema

NameRequiredDescriptionDefault
urlYes
noteYes
hintsNo
totalNo
accessNoWhether this result is shown in full through this server: public = yes; not_public_now = the item exists but this server does not return it at present (e.g. a notice whose deadline has passed); login_required / plan_required = the item exists but is available only under other access conditions of the site (sign-in, or a plan)
groupsNo
sourceYes
appliedYes
cite_asNoOne-line source citation for this result: the page title on 入札案件観測所, the data date, and the URL of that page (same as `url`).
messageNo
relatedNoFacts related to this result (counts) and the tool call that returns them
resultsNo
returnedYes
retrievedYes
candidatesNo
data_as_ofYes
restrictedNoItems that exist but are not returned here, with their access value. An item listed here is not missing from the data.
next_cursorNo
period_noteNo
total_all_periodsNoWhen a period (date_from, date_to or fiscal_year) is given: the count for the same conditions without the period

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / hints / items / properties / try_keyword
      Added value: +{
      +  "description": "A different wording of the keyword (synonym) and how many records it matches; call again with keyword set to this",
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds the substantive behavior an agent cannot get from annotations: counting only covers records that reached award/contract, with 不調/中止/結果未確定 broken out into not_awarded, and amounts reported as bands rather than exact figures.

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?

Front-loaded with the trigger, then constraint, then counting semantics; sentences are dense but each carries information. The trailing keyword list ('落札結果・契約結果・落札者・随意契約') is retrieval stuffing rather than instruction and is the only real padding.

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?

An output schema exists, so return format need not be described, and pagination/limit/cursor live in the schema. The description covers the non-obvious pieces (award vs not_awarded counting, 2004 coverage, bands, the at-least-one rule) well enough to call correctly; it stops short of describing result-volume expectations for a 10-row page cap.

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%, so the schema already carries per-parameter meaning (status values, group_by modes, area/category equivalents) and the baseline is 3. The description does add one genuinely schema-absent cross-parameter constraint ('at least one of keyword, buyer, supplier or a non-default status is required', notable because required is empty), but beyond that it largely restates 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 concrete resource and scope: 'award and contract results from 2004 onward for national agencies and local governments', with an explicit trigger ('who won, or how often'). It implicitly separates itself from notice/plan siblings (post-award vs pre-award) but never names a sibling tool, so differentiation is inference rather than statement.

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?

Clear trigger conditions ('user asks who won, or how often') plus a routing rule for the two modes: rows by default, 'set group_by to get counts instead of rows'. It also states a hard precondition (at least one of keyword/buyer/supplier/non-default status). No explicit when-not-use or named alternative is given.

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