NZ Police Recorded Crime Victims Statistics by police district. Victimisations by offence type, age group, and sex. Monthly series from 2021; cron caches the latest year per district. Source: policedata.nz victimisations-demographics CSV.
| Name | Required | Description | Default |
|---|---|---|---|
| region | Yes | NZ Police district, e.g. "Auckland City", "Canterbury", "Wellington", "Counties Manukau" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It adds useful facts about provenance and cron caching, but it does not mention return format, pagination, or failure behavior, leaving some ambiguity for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences deliver the core purpose, time range, caching behavior, and source with zero fluff. The most important identifying information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool, the description covers the dataset's content, geography, time span, and provenance. However, because there is no output schema, it would be stronger if it explicitly noted the expected response shape, such as a table or series of counts.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single 'region' parameter is fully described in the schema with concrete examples, so schema coverage is 100%. The description loosely reinforces that data is organized by police district but adds no meaningful semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description precisely identifies the resource (NZ Police Recorded Crime Victims Statistics), the geographic scope (police district), and the breakdown dimensions (offence type, age group, sex). It is clearly distinguishable from sibling tools like nz-demographics and nz-income.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly signals use for New Zealand crime victim data via its content and source attribution, but it never explicitly states when to use this tool versus alternatives. Temporal and caching notes provide context but no selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool maps to a clearly distinct dataset or lookup, with country prefixes and topic names separating overlapping domains. Even similar tools like au-abs-building-activity and au-abs-building-approvals are unambiguously differentiated by their descriptions.
The data tools follow a consistent country/topic hyphenated pattern (au-*, nz-*), making resource selection predictable. The meta tools (get_catalog, list_services, health) break this pattern with imperative/underscore names, but this is a minor and understandable deviation.
At 26 tools, the set is on the heavy side and slightly exceeds the typical comfortable range. However, each tool represents a genuinely distinct data service, and the clear grouping by country and topic keeps the surface navigable.
The server covers a broad range of common agent data needs for Australia and New Zealand: demographics, income, building, labour, weather, time, holidays, school terms, and place resolution. Minor gaps exist, such as no NZ building data or broader international coverage, but core workflows are well supported.