Distil — Machine-Native Public Data Refinery

Search EU TED Public Tenders

search_eu_tenders

Read-onlyIdempotent

Searches across European Union TED public procurement tenders by keyword, CPV sector, and member state country code.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of tender notices to return (default 5, max 20).
`query`	Yes	Procurement search keyword, project name, or sector term (e.g. 'Cybersecurity', 'Cloud').
`country`	No	Two-letter ISO country code filter (e.g. 'FR', 'DE', 'IT', 'ES', 'NL').
`forceFresh`	No	Spend Control: When true, bypasses Edge KV cache and forces a real-time statutory primary registry call (applies 2.5x Freshness Inconvenience Surcharge). Default: false.
`maxAgeHours`	No	Spend Control: Maximum acceptable data age in hours (e.g. 48 for 2 days tolerance). If cache satisfies this, delivers sub-5ms at standard 1.0x Economy rate. Set to 0 to force live primary fetch.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`content`	Yes
`isError`	No

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description does not go further to disclose list size, pagination, source freshness, or cost behavior, but it aligns with annotations and adds the registry scope. With annotations carrying the burden, this is adequate but not rich.

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?

Single sentence with no filler; the verb and main resource come first, followed by filter dimensions. Every word carries meaning and no schema content is repeated unnecessarily.

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?

Between the detailed input schema, output schema, and annotations, most invocation concerns are covered. The main gap is the lack of routing guidance among sibling search/get tender tools, but the description plus name make the tool's role recognizable.

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 the baseline is 3; the schema already documents query, limit, country, forceFresh, and maxAgeHours precisely. The description adds the 'CPV sector' interpretation of query and the country-code filter, which slightly reinforces but does not significantly expand on 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?

States a specific verb ('Searches'), a specific resource (EU TED public procurement tenders), and the filtering axes (keyword, CPV sector, country code). This clearly distinguishes it from sibling getters like get_eu_public_tender and country-specific search_es_tenders, even without naming them.

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

Usage Guidelines2/5

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

No guidance is given on when to choose this tool over siblings such as get_eu_public_tender or search_es_tenders, and no prerequisites or exclusions are mentioned. The intended use must be inferred from the tool name and resource description rather than explicitly stated.

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

All Distil — Machine-Native Public Data Refinery tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool maps to a distinct data product: country-specific filings, tender records/search, risk scoring, sanctions screening, and entity graphs. The search/get split cleanly separates discovery from retrieval, and even similar country-specific tools are clearly qualified by region and entity type.

Naming Consistency5/5

All tools use a consistent snake_case verb_noun pattern: get_* for retrieval and search_* for discovery, with country or region qualifiers where applicable. Cross-cutting tools like get_corporate_risk_score and get_tender_intelligence fit the same pattern without feeling out of place.

Tool Count4/5

At 16 tools, the server is slightly above the ideal 3-15 range, but the multi-country, multi-domain scope justifies nearly every tool. The set is heavier than a tightly focused server, yet no tool feels redundant.

Completeness4/5

The set covers the core read-only workflow well: search to find entities or tenders, get to retrieve records, plus analytical tools for risk, sanctions, and tender intelligence. Minor gaps exist, such as no Spanish company registry access and no UK tender search, but these are workable and do not block primary due-diligence workflows.

Resources

Need Help?