Skip to main content
Glama
qune-tech

qune-tech/ocds-mcp

match_tenders

Match company profiles to relevant public procurement tenders using semantic similarity search. Filter results by CPV codes, procurement methods, value ranges, deadlines, and buyer criteria to identify suitable opportunities.

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 full burden and provides good behavioral context: it explains the matching mechanism (semantic similarity via KNN cosine search), result enrichment, deduplication logic (by OCID, keeping highest score), and filtering capabilities. However, it doesn't mention rate limits, error conditions, or response format details.

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?

The description is efficiently structured in three sentences: first explains the core matching process, second lists filtering options, third covers deduplication. Every sentence adds essential information with zero wasted words.

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

Completeness3/5

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

For a complex tool with 15 parameters and no annotations/output schema, the description provides good operational context but lacks details about return values, error handling, performance characteristics, or integration with sibling tools (e.g., requiring an existing profile from 'create_company_profile').

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 fully documents all 15 parameters. The description adds marginal value by mentioning that filtering can be done by 'CPV prefix, category, method, value range, buyer name, deadline, and status', which aligns with parameter names but doesn't provide additional semantics beyond the schema.

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 the tool's purpose with specific verbs ('match', 'enriched', 'post-filter', 'deduplicates') and resources ('company profile', 'tenders', 'semantic similarity', 'KNN cosine search', 'release metadata'). It distinguishes from siblings like 'search_text' by focusing on profile-based matching rather than text search.

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

Usage Guidelines3/5

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

The description implies usage context through terms like 'semantic similarity' and 'post-filter', but doesn't explicitly state when to use this tool versus alternatives like 'search_text' or 'list_releases'. No guidance on prerequisites (e.g., profile must exist) or exclusions is provided.

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/ocds-mcp'

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