Skip to main content
Glama

Diavgis — Greek Public Procurement

by gr.diavgis

Get One Act

get_act
Read-onlyIdempotent

Full detail of one act by its id (Διαύγεια ΑΔΑ, ΚΗΜΔΗΣ 'kimdis:<ΑΔΑΜ>', or TED 'ted:'): canonical fields, resolved buyer/supplier entities, CPV codes with labels, and its cross-source lifecycle chain if linked. On ΚΗΜΔΗΣ contracts, commitment_ada carries the Διαύγεια ΑΔΑ of the budget-commitment decision the source declares (comma-separated when more than one). It is a pointer INTO Διαύγεια, not an act we necessarily hold — resolve it at diavgeia.gov.gr, not through this API — and it is deliberately NOT a chain edge: one annual commitment funds many unrelated contracts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
adaYesact id — ΑΔΑ, 'kimdis:<ΑΔΑΜ>' or 'ted:<number>'

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
actYes
cpvsYesCPV classifications with their official Greek labels
buyerYes
chainYes
supplierYes

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already indicate read-only, idempotent, open-world behavior. The description adds substantial behavioral nuance: the API may not hold the commitment_ada act, the field can be comma-separated, it is not a chain edge, and external resolution is required. This goes well beyond the annotations.

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 front-loaded with the core purpose, then adds only high-value caveats about commitment_ada and chain semantics. Each sentence earns its place, and the length is justified by the cross-source complexity.

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?

Given the output schema exists and annotations cover safety, the description is complete enough: it explains all id formats, output scope, the special commitment_ada behavior, and the important non-chain relationship. Nothing essential is missing.

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 parameter is already well documented. The description restates the id formats but adds little beyond the schema. A baseline of 3 is appropriate since the schema carries the parameter-semantics burden.

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: 'Full detail of one act by its id' with the accepted id forms. It also distinguishes the tool from siblings like get_chain by explicitly clarifying that commitment_ada is 'deliberately NOT a chain edge' and from search/entity tools by focusing on a single act lookup.

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 implies use when one already has an act id and gives explicit when-not guidance: commitment_ada must be resolved at diavgeia.gov.gr, 'not through this API.' It does not explicitly name sibling alternatives such as get_chain or search_tenders, so it stops short of a full 5.

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

All Diavgis — Greek Public Procurement toolsInspect
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

A4.4/5.0
Disambiguation4/5

Each tool targets a distinct concern: entity resolution, entity profiles, counterparties, rankings, spend aggregates, search, act detail, lifecycle chains, expiring contracts, and quota. Minor overlap exists between get_act and get_chain since get_act can include lifecycle chain data, but the descriptions make the intended primary use clear.

Naming Consistency4/5

All names use snake_case and most follow a verb_noun pattern like find_entity, get_entity, search_tenders, and rank_entities. A few tools such as entity_counterparties and expiring_contracts are noun-phrase names, and spend_by_cpv uses a different structure, so the pattern is mostly consistent but not uniform.

Tool Count5/5

Ten tools is well-scoped for a Greek public procurement data API: the count is large enough to cover discovery, search, entity analytics, spend analytics, lifecycle detail, and quota management without feeling bloated. Each tool appears to earn its place with no obvious redundant duplicates.

Completeness5/5

The tool surface covers the full read-only procurement workflow: resolve names to tax IDs, profile entities, find counterparties, rank entities, search tenders with filters, inspect individual acts, follow lifecycle chains, monitor expiring contracts, and aggregate spend by CPV. There are no major missing operations for the stated purpose.

Resources