The Cracks Index

Compare Dutch municipalities on the social domain

compare_gemeenten

Read-onlyIdempotent

Compare the social-domain profile of several Dutch municipalities.

Given two to six CBS GM-codes, returns a side-by-side comparison of their
four v1 social-domain indicators plus composite score and rank. Useful
for an agent answering "how does municipality A compare to B on the
social domain".

Read-only, no personal data. wmo_pressure and youth_care_load are context
only — shown but never scored. CBS aggregates describe an area, not its
quality. Netherlands-only.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`region_codes`	Yes	Two to six CBS GM-codes of Dutch municipalities, comma-separated, e.g. 'GM0363,GM0599,GM0518'. Case-insensitive.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.5/5.0

Behavior5/5

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

The description adds meaningful context beyond the annotations: it explicitly states 'Read-only, no personal data' (reinforcing but adding 'no personal data'), clarifies that 'wmo_pressure and youth_care_load are context only — shown but never scored', and provides interpretive guidance ('CBS aggregates describe an area, not its quality'). These are behaviors not visible in the annotations or schema.

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 compact and front-loaded: the first sentence states the purpose, the second explains input and output, and the third adds key caveats. No redundant sentences; every clause carries useful information. It is appropriately sized for a tool with one parameter and existing schema/annotations.

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?

For a tool with one parameter fully documented in the schema and an output schema present, the description covers the essential context: use case, input range, what is returned (indicators, composite score, rank), and important caveats (context indicators not scored, area-level aggregates). Nothing critical is missing for the agent to select and invoke correctly.

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?

The only parameter, region_codes, is fully described in the schema with format, example, and constraints (two to six comma-separated GM-codes, case-insensitive). The description repeats 'two to six CBS GM-codes' but adds no new semantic detail beyond what the schema already provides. With 100% schema coverage, the 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?

The description begins with a clear, specific verb+resource: 'Compare the social-domain profile of several Dutch municipalities.' It further details the exact scope (two to six CBS GM-codes, four v1 indicators plus composite score/rank) and distinguishes from siblings by being explicitly Netherlands-specific and focused on social-domain comparison, unlike compare_countries or gemeente_social_profile.

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 says it is 'Useful for an agent answering how municipality A compares to B on the social domain', which gives a clear use case. It also includes a boundary ('Netherlands-only') and specifies the input range (two to six codes). However, it does not explicitly name alternatives or state when NOT to use it, so it falls short of the full 5.

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

All The Cracks Index 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

A4.1/5.0

Disambiguation5/5

Each tool targets a distinct query: rankings, country details, region details, comparisons, trends, correlations, methodology, and improvement guidance. Despite minor overlaps (e.g., country_fix and improvement_guidance), descriptions clearly differentiate them, so an agent can reliably select the correct tool.

Naming Consistency3/5

Tool names mix patterns: some start with verbs (compare_countries, get_cracks_index), others with nouns (area_statistics, country_detail, methodology). While readable and clear, the lack of a consistent verb_noun or noun_verb paradigm reduces predictability for an agent.

Tool Count5/5

With 13 tools covering the full spectrum of index queries—rankings, details, comparisons, trends, correlations, methodology, and improvement guidance—the count is well-scoped for the domain. No tool feels superfluous, and the set is neither too sparse nor too bloated.

Completeness5/5

The tool surface provides complete CRUD-like coverage for the Cracks Index: full ranking, per-area detail and breakdown, comparisons, trends, top movers, indicator correlations, ranking by indicator, methodology, and improvement guidance. No obvious gaps exist for common agent workflows.

Resources

Need Help?