Ärikratt

Procurement market statistics

procurement_stats

Read-only

Compare legal-entity buyer and Common Procurement Vocabulary (CPV) markets across retained history. Notices, procedure folders and observed notice-lots are separate; revisions remain separate lots. Includes tender-count coverage, single-tender share with known denominator, observed winner coverage and year/buyer/category tables. Rates below five observations are withheld. Indicators are not findings, corruption scores or expenditure. Estonian Public Procurement Register attribution accompanies results. Tables have up to 50 rows; truncated results retain totals. Old snapshots return available=false and empty tables. Use procurement_notices for individual notices and open tenders. Do not look up natural persons.

Input Schema

Name	Required	Description	Default
`cpv`	No	Common Procurement Vocabulary (CPV) prefix
`buyer`	No	Buyer name or registry-code contains match

Output Schema

Name	Required	Description
`cpv`	No
`note`	No
`as_of`	Yes
`buyers`	No
`by_year`	No
`sources`	Yes
`summary`	No
`available`	No
`cpv_total`	No
`truncated`	No
`disclaimer`	Yes
`snapshot_id`	Yes
`buyers_total`	No
`by_year_total`	No
`source_details`	Yes	Full attribution and acquisition evidence: source_metadata(key).
`omitted_sections`	No	Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 18, 2026

addedOutput schema / properties / omitted_sections

Added value: +{
+  "description": "Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / source_details

Added value: +{
+  "description": "Full attribution and acquisition evidence: source_metadata(key).",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / sources / items / properties / as_of
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
addedOutput schema / properties / sources / items / properties / key
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```

changedOutput schema / required

Previous value: -[
-  "snapshot_id",
-  "as_of",
-  "sources",
-  "disclaimer"
-]New value: +[
+  "snapshot_id",
+  "as_of",
+  "sources",
+  "source_details",
+  "disclaimer"
+]

Changed1 schema field changedOct 10, 2026
- changedInput schema / properties / cpv / description
```
Previous value: -"CPV prefix"New value: +"Common Procurement Vocabulary (CPV) prefix"
```
AddedOct 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantive behavior beyond them: small-sample suppression ('Rates below five observations are withheld'), row truncation and totals retention, legacy snapshot behavior ('available=false and empty tables'), and an explicit disclaimer that indicators are not findings or corruption scores.

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-loaded with the core comparison purpose before scope caveats and routing. It is dense with eight clauses and some statements (attribution, notice-lot separation) are more peripheral, but nearly every sentence carries operational information.

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?

Despite an output schema existing, the description still supplies the edge cases an agent needs: suppression thresholds, truncation limits, empty/false results for old snapshots, and interpretation limits. Nothing essential to correct invocation or interpretation 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% for both params (cpv prefix, buyer name/registry-code contains match), so the schema carries parameter meaning. The description only obliquely references buyer/category/year tables and adds no syntax or matching semantics beyond the schema; a baseline 3 is appropriate.

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 (Compare) and resource (legal-entity buyer and CPV markets) with explicit scope (across retained history), and draws the line against the sibling procurement_notices. An agent can distinguish this aggregation tool from the notice-listing tool without opening either 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?

Names the alternative tool explicitly ('Use procurement_notices for individual notices and open tenders') and gives a negative boundary ('Do not look up natural persons'). It stops short of stating the full when-to-use condition (e.g. when a market-comparison question is being asked versus a single-entity lookup), so it is clear but not exhaustive.

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

All Ärikratt 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?