Skip to main content
Glama
Sign In

Germany Tenders

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Germany Search Tenders

germany_search_tenders
Read-onlyIdempotent

Search official GERMAN government public-procurement tenders (Öffentliche Vergabe / Ausschreibungen) from the federal Bekanntmachungsservice open-data feed (oeffentlichevergabe.de), Open Contracting Data Standard (OCDS, CC0). Returns each notice shaped: ocid, title, buyer/Vergabestelle, contract value in EUR, procurement category, CPV code, procurement method, submission deadline, and publish date. Filter by publish-date range and/or a keyword (matched against title, description, buyer, and CPV description — German text). Defaults to the most recent days if no dates given. Can answer wide date ranges (months) as well as very recent days. Data covers Germany only.

Input Schema

NameRequiredDescriptionDefault
limitNoMax number of tenders to return (default 25, max 100). Results are newest-first.
queryNoOptional keyword to filter on (case-insensitive substring match against title, description, buyer name, and CPV description — German). Omit to return all notices in the date range. E.g. "Bauarbeiten", "Software", "Reinigung".
date_toNoLatest PUBLISH date to include, YYYY-MM-DD. Defaults to today.
date_fromNoEarliest PUBLISH date to include, YYYY-MM-DD. Defaults to ~30 days ago. A very old date may only partly be covered; see the response for how much of the range came back.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / date_from / description
      Previous value: -"Earliest PUBLISH date to include, YYYY-MM-DD. Defaults to ~30 days ago (only the most recent 3 days of that window are fetched per call — narrow the range for older notices)."New value: +"Earliest PUBLISH date to include, YYYY-MM-DD. Defaults to ~30 days ago. A very old date may only partly be covered; see the response for how much of the range came back."
  2. Changed1 schema field changed
    • changedInput schema / properties / date_from / description
      Previous value: -"Earliest PUBLISH date to include, YYYY-MM-DD. Defaults to ~30 days ago (only the most recent 7 days of that window are fetched per call — narrow the range for older notices)."New value: +"Earliest PUBLISH date to include, YYYY-MM-DD. Defaults to ~30 days ago (only the most recent 3 days of that window are fetched per call — narrow the range for older notices)."
  3. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "date_from": "2024-11-01",
+    "date_to": "2024-11-15",
+    "limit": 25,
+    "query": "Bauarbeiten"
+  },
+  {
+    "date_to": "2024-11-15",
+    "limit": 50
+  }
+]
  4. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is lower, and the description adds real value beyond them: the authoritative source and license, the Germany-only coverage boundary, and default date behavior. It does not mention pagination beyond limit or any rate limits, keeping it from 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?

Front-loads the core purpose and source, then the return shape, then filtering, then scope. Dense but efficient; there is mild repetition between the description's keyword/filter phrasing and the schema, though the return-shape list is justified by the absent output 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?

With no output schema, the description helpfully enumerates returned fields, and it covers source, filtering, defaults, and geographic scope. It stops short of explaining how to retrieve beyond the 100-result limit or depth of historical coverage, which slightly limits an agent calling it at scale.

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 documents all four parameters in detail. The description largely restates what the schema provides (keyword matched against title/description/buyer/CPV, German text) without adding new syntax or format guidance, so the baseline of 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?

States a specific verb and resource (search German government procurement tenders), names the exact data source (Bekanntmachungsservice / oeffentlichevergabe.de) and standard (OCDS, CC0), and lists what each notice contains. This clearly distinguishes it from the sibling germany_buyer_spend_history and germany_supplier_win_history tools, which cover spend/win history rather than a notice search.

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?

Explains the filtering model (publish-date range and/or keyword) and the default behavior when no dates are supplied, plus that it handles both wide and narrow ranges. It does not explicitly name when to prefer a sibling (e.g. buyer_spend_history) over this, so it stops short of full alternative routing.

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

All Germany Tenders toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources