Skip to main content
Glama

入札案件観測所

受付中の入札公告を探す

search_bid_notices
Read-onlyIdempotent

Use this when the user asks which public tenders are open now in Japan (national agencies, prefectures, municipalities), by keyword, area, category, buyer or deadline. Returns up to 10 notices, nearest deadline first, with the total count. Not for past results: use search_awards. Includes nominated tenders and requests for comments, marked by notice_type; use types to leave them out. For tenders not yet announced, use search_bid_plans. 受付中の入札公告・公募・プロポーザル・見積合わせ・指名競争・意見招請(官公需・調達)

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_bid_notices"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoPrefecture. Accepts 福岡県, 福岡, Fukuoka, 40 (JIS code), national (国の機関)
sortNodeadline (default): nearest deadline first. newest: most recently published first.
buyerNoProcuring entity: name (part of it is fine, e.g. 福岡市) or a buyer_id
limitNoRows per page, 1-10 (default 10)
typesNobid = tenders anyone qualified can apply for; nominated = 指名競争入札, only companies the buyer nominates can bid (no application); opinion = 意見招請・資料提供招請, requests for comments or information, not a tender; items = small goods purchases listing many items in one notice. Default: all types (the same as the site's open list).
cursorNonext_cursor from the previous result, with the same other arguments. Up to 3 pages.
keywordNoWords in the title or summary. Space = AND. Example: 庁舎 清掃
categoriesNoOne or more of: 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
deadline_toNoDeadline on or before this date, YYYY-MM-DD
changed_sinceNoOnly notices that are new or whose title, deadline, method, eligibility, procedure, period or place changed on or after this date, YYYY-MM-DD (for example yesterday, for "what is new or changed since yesterday"). Each result then has `changes`. Changes are recorded once a day; `changes_tracked_since` in the result says from when.
deadline_fromNoDeadline on or after this date, YYYY-MM-DD. The result's `today` field gives the current date in Japan. A deadline range leaves out notices whose deadline could not be read; `deadline_unknown_count` in the result says how many of those match the other conditions.
response_formatNoconcise (default): fewer fields per row. detailed: adds IDs, method, original URL and retrieval date per row.

Output Schema

NameRequiredDescriptionDefault
urlYes
noteYes
hintsNo
todayYes
totalYes
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)
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
resultsYes
returnedYes
retrievedYes
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
deadline_noteNo
no_area_countNo
deadline_unknown_countNo

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. Changed2 schema fields changed
    • addedInput schema / properties / changed_since
      Added value: +{
      +  "description": "Only notices that are new or whose title, deadline, method, eligibility, procedure, period or place changed on or after this date, YYYY-MM-DD (for example yesterday, for \"what is new or changed since yesterday\"). Each result then has `changes`. Changes are recorded once a day; `changes_tracked_since` in the result says from when.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / changes
      Added value: +{
      +  "description": "With changed_since: what happened to this notice on or after that date (new, or which field changed with before/after)",
      +  "items": {
      +    "additionalProperties": {},
      +    "properties": {
      +      "day": {
      +        "type": "string"
      +      },
      +      "field": {
      +        "type": "string"
      +      },
      +      "kind": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "day",
      +      "kind"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds genuinely new behavior: up to 10 notices per page ordered by nearest deadline, a total count in the result, a three-page pagination cap, and the fact that changes are recorded only once a day (with `changes_tracked_since` reporting the window). It also discloses that nominated tenders and requests for comments are mixed in and tagged by `notice_type`. It does not discuss failure modes or empty-result behavior, so it falls short of a 5.

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 most important information (what it returns and which siblings to avoid) is front-loaded, and each sentence carries a distinct fact rather than repeating the title. The trailing Japanese phrase listing synonyms (公募・プロポーザル・見積合わせ・指名競争・意見招請) is somewhat redundant with the body but does broaden query matching, so it earns partial keep.

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

Completeness5/5

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

For a 12-parameter, zero-required search tool with a full output schema, the description covers purpose, ranking, result caps, pagination, special notice types, and sibling routing, so an agent needs nothing else to call it correctly. Return-value detail is correctly delegated to the output schema.

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 enum meanings, date formats, and cursor semantics; the description only echoes the filter dimensions (keyword, area, category, buyer, deadline) and points at `types` for excluding nominated/opinion notices. That adds orientation but no syntax or edge-case detail 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.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('which public tenders are open now in Japan') plus the filterable dimensions and the geographic scope (national agencies, prefectures, municipalities). It explicitly distinguishes itself from search_awards (past results) and search_bid_plans (not yet announced), so an agent can separate it from its siblings without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The trigger condition is stated up front ('Use this when the user asks which public tenders are open now...'), followed by two explicit exclusions that route to alternatives: past results go to search_awards, unannounced tenders go to search_bid_plans. It even tells the agent how to suppress nominated/opinion notices via `types`, which is a concrete in-tool alternative to a different call.

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