Romania Tenders

Ro Direct Acquisitions

ro_direct_acquisitions

Read-onlyIdempotent

ROMANIAN direct acquisitions (achizitii directe) from the SEAP / SICAP electronic catalogue: the small-value purchases Romanian public bodies make from suppliers, ~1,600 a day. Returns the newest ones first from a trailing window (default last 6 hours; ordering is stated in the response; published times are UTC), optionally narrowed by a name keyword (e.g. "calculatoare", "combustibil"). Each is shaped compact: unique acquisition code (DA...), name, state, CPV code, contracting authority, supplier, estimated and closing value in RON, publish time and deadlines.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "hours": 6,
      "limit": 5
    },
    "name": "ro_direct_acquisitions"
  }
}

Input Schema

Name	Required	Description
`hours`	No	Trailing window in hours (default 6, max 720). Windows busier than 2000 acquisitions are capped by the source and flagged in the response.
`limit`	No	Max acquisitions to return (default 20, max 100).
`query`	No	Optional keyword matched against the acquisition name (Romanian).
`date_to`	No	Latest PUBLISH date, YYYY-MM-DD (default: now).
`date_from`	No	Earliest PUBLISH date, YYYY-MM-DD (overrides hours).

Output Schema

Name	Required	Description	Default
`count`	No
`source`	No
`window`	No
`data_as_of`	No
`acquisitions`	No
`total_in_window`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds real operational context beyond that: publish times are UTC, ordering is echoed in the response, and busy windows are capped at ~2,000 by the source — genuinely useful for interpreting results, though it stops short of discussing paging or error behavior.

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 lead sentence front-loads the resource and its domain meaning, and each subsequent clause adds information (volume, ordering, defaults, narrowing, output shape). It is dense but a single long paragraph with some redundancy around the 'compact' record fields that an output schema already covers.

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 read-only listing tool with five optional parameters, full schema coverage and an existing output schema, this description supplies everything an agent needs: domain meaning, defaults, time zone, ordering, and capping caveats. The listed record fields are a helpful preview rather than a required explanation, since the output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage the baseline is 3, and the description earns an extra point by tying the date/window parameters to behavior (default last 6 hours, UTC publish times) and by giving concrete keyword examples for `query` in Romanian. It does not re-explain the max values, which the schema already handles.

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 states a specific verb and resource ('direct acquisitions from the SEAP/SICAP electronic catalogue') and scopes it precisely as 'small-value purchases Romanian public bodies make from suppliers, ~1,600 a day'. The parenthetical Romanian term and the explicit definition of what a direct acquisition is separates it from the tender-notice sibling without needing 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 Guidelines4/5

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

It explains the default operating mode (newest first, trailing window of 6 hours) and the one narrowing option ('optionally narrowed by a name keyword'), giving examples like "calculatoare" and "combustibil". It never states when NOT to use it or names a concrete alternative such as ro_tender_notices, so the routing guidance is clear but not exhaustive.

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

All Romania Tenders tools Inspect

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.