Skip to main content
Glama
qune-tech

qune-tech/ocds-mcp

match_tenders

Match a company profile with tenders using semantic similarity, then filter results by CPV prefix, buyer name, deadline, value range, and other criteria.

Instructions

Match a company profile against tenders using semantic similarity. The profile's embedding is sent to the REST API for KNN cosine search against all tender chunks. Results are enriched with release metadata from the API and can be post-filtered by CPV prefix, category, method, value range, buyer name, deadline, and status. Deduplicates by OCID (keeps highest score).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
buyer_nameNoFilter by buyer name (case-insensitive substring match)
cpv_prefixNoFilter by CPV code prefix (e.g. '45' for construction, '72' for IT)
deadline_afterNoOnly include tenders with deadline on or after this ISO-8601 datetime
deadline_beforeNoOnly include tenders with deadline on or before this ISO-8601 datetime
eu_fundedNoFilter by EU funding status (true = EU funded)
has_awardsNoFilter by whether the release has awards with suppliers (true/false)
kNoNumber of matching tenders to return (default: 10)
location_nutsNoFilter by delivery location NUTS code prefix (e.g. 'DE3' for Berlin)
main_procurement_categoryNoFilter by main procurement category (e.g. 'works', 'goods', 'services')
procurement_methodNoFilter by procurement method (e.g. 'open', 'selective', 'limited')
profile_idYesThe UUID of the company profile to match against tenders
statusNoFilter by tender status (e.g. 'active', 'complete', 'cancelled')
tagNoFilter by lifecycle tag (e.g. 'tender', 'award', 'planning')
value_maxNoMaximum tender value
value_minNoMinimum tender value
Behavior4/5

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

With no annotations, the description carries the burden. It explains the algorithm (semantic similarity, KNN search, enrichment, dedup), but does not disclose read-only nature, auth, or rate limits. The behavior is well-described but some aspects are missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action. Each sentence is informative and necessary: method, filters, dedup. No redundancy.

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?

Given 15 parameters and no output schema, the description explains the matching algorithm and filtering but does not describe the return format or enriched metadata contents. Still fairly complete for a complex tool.

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 coverage is 100%, so baseline is 3. The description adds context about post-filtering but does not significantly enhance parameter meaning beyond the schema descriptions.

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 clearly states it matches a company profile against tenders using semantic similarity, describes the process (embedding, KNN cosine search, enrichment, filtering, deduplication), and distinguishes itself from sibling tools like search_text and list_releases.

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?

The description provides clear context for use (finding semantically similar tenders to a profile) and lists extensive filtering options, but does not explicitly state when not to use it or name alternative tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/qune-tech/vergabe-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server