Evolc Signals

Search open public tenders

search_tenders

Read-only

Open calls for tenders from public buyers across Europe (TED, the EU tenders journal), closing soonest first. Each tender has the buyer, category (CPV), estimated value, deadline and fit_count: how many Evolc companies won public tenders in the same CPV class since 2024. Pass company (an Evolc slug) to get the open tenders in the categories that company already wins, or filter by country, CPV division and text. Titles are in the buyer's language. The tender page (url) links to where offers are submitted.

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_tenders"
  }
}

Input Schema

Name	Required	Description
`q`	No	Title, buyer or category contains this text (titles are in the local language).
`fit`	No	Only tenders where at least one Evolc company won similar work.
`limit`	No	Tenders to return.
`nature`	No	Works, supplies or services.
`offset`	No	Skip this many tenders.
`company`	No	Evolc company slug: return open tenders in the CPV classes this company won before (other filters are ignored).
`countries`	No	Buyer country, ISO-2.
`divisions`	No	CPV divisions (first two digits): 14 Mining & basic metals; 15 Food & beverages; 16 Agricultural machinery; 18 Clothing, footwear & accessories; 19 Leather, textiles, plastic & rubber; 22 Printed matter; 24 Chemical products; 30 Office & computer equipment; 31 Electrical equipment & lighting; 32 Telecom & radio equipment; 33 Medical equipment & pharmaceuticals; 34 Vehicles & transport equipment; 35 Security, fire & defence equipment; 37 Sports goods, toys & instruments; 38 Laboratory & precision equipment; 39 Furniture & cleaning products; 41 Water; 42 Industrial machinery; 43 Mining & construction machinery; 44 Construction materials; 45 Construction work; 48 Software & information systems; 50 Repair & maintenance; 51 Installation services; 55 Hotels, catering & retail; 60 Transport services; 63 Transport support & travel; 64 Postal & telecom services; 65 Public utilities; 66 Financial & insurance services; 70 Real estate services; 71 Architecture & engineering; 72 IT services & software development; 73 Research & development; 75 Public administration services; 76 Oil & gas services; 77 Agricultural & forestry services; 79 Business services: legal, marketing, consulting; 80 Education & training; 85 Health & social work; 90 Waste, cleaning & environmental services; 92 Recreation, culture & sport; 98 Other community services; 03 Agriculture, farming & forestry products; 09 Fuel, energy & electricity.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuinely non-obvious behavior — result ordering by deadline, titles in the buyer's language, and the meaning of fit_count (count of Evolc companies that won in the same CPV class since 2024). It also explains that url points to the submission page. Pagination behaviour and index freshness are the only notable omissions.

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 what the tool returns and the sort order, then moves to how to filter and what the response fields mean. All four sentences carry information; the only redundancy is the company/filter interplay already present in 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?

With eight optional parameters, no output schema and no annotation detail on results, the description does the necessary work by explaining the response shape (buyer, CPV, value, deadline, fit_count, url) and the two query modes. It is complete enough to call correctly; the nature parameter and pagination defaults are left entirely to the schema, which is acceptable but leaves a small gap.

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 every parameter including the division code legend is already documented; the baseline of 3 applies. The description does reinforce the interaction rule that company causes other filters to be ignored, but the schema already states this, so it adds little beyond restating structured data.

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 (open calls for tenders from public buyers across Europe via TED) plus the default ordering (closing soonest first) and the record fields returned. An agent can distinguish this from search_moves and search_signals purely from the resource described, without opening any 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?

Gives concrete routing logic: pass a company slug to see tenders in CPV classes that company already wins, otherwise filter by country, CPV division and text. The two modes are clearly separated. It stops short of naming a sibling alternative or stating when not to use this tool, so it is short of a 5.

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

All Evolc Signals 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.

Resources

Need Help?