Skip to main content
Glama

Gets Nz

by io.github.pipeworx-io

Nz Tender Search

nz_tender_search
Read-onlyIdempotent

Search open New Zealand government tenders on GETS by keyword — matches tender titles, buying agency names, UNSPSC categories, regions, and the tender overview text. Use for questions like "NZ government tenders for cybersecurity", "Wellington council procurement", "open RFPs from the Ministry of Health". Returns matching tenders with reference, title, agency, close date, region, categories, a short overview snippet, and the public GETS URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum matches to return (1-100). Default 25.
queryYesKeywords to search for, e.g. "road maintenance", "software", "consultancy", "Christchurch".

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "query": "cybersecurity"
+  },
+  {
+    "limit": 100,
+    "query": "Wellington council IT services"
+  }
+]
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, establishing a safe, read-only operation. The description adds valuable behavioral context: search scope (keywords applied to multiple fields), return fields (reference, title, agency, close date, region, categories, snippet, URL), and the fact that it returns a public URL. No contradictions with 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 concise: three sentences covering purpose, examples, and return fields. It is front-loaded with the action and scope, with every sentence providing essential information. No filler or redundancy.

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 2 parameters, full schema descriptions, and no output schema, the description compensates by listing what the output contains. It explains the search scope and return fields adequately. The tool is simple (keyword search), and the description covers the key aspects a user needs to understand its behavior.

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%, with both 'query' and 'limit' having descriptions. The description adds that the query matches across multiple fields (titles, agency names, etc.) but does not add new technical constraints or formats beyond what the schema provides. The limit parameter's range and default are already in the schema. Thus, the description adds marginal value over the schema, meeting the baseline for high coverage.

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 clearly states it searches open New Zealand government tenders on GETS by keyword, specifies fields matched (titles, agency names, UNSPSC categories, regions, tender overview text), and provides example queries and return fields. This is a specific verb-resource combination that distinguishes it from sibling tools like nz_tender_detail (which likely retrieves detailed info) and nz_tender_open (which may list all open tenders).

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 explicitly states 'Use for questions like ...' providing clear context for typical queries (e.g., 'NZ government tenders for cybersecurity'). However, it does not provide explicit when-not-to-use guidance or mention alternative tools for more specific needs (e.g., nz_tender_detail for a known tender ID). This makes it slightly less than fully comprehensive, but still clear on intended use cases.

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

All Gets Nz 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

A3.8/5.0
Disambiguation2/5

Multiple tools overlap significantly: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded serve nearly identical purposes, and deep_research further duplicates. Polymarket tools (bet_research, polymarket_arbitrage, polymarket_edges, etc.) also have overlapping scopes, making it hard for an agent to select the correct one without deep inspection.

Naming Consistency3/5

Tool names use a mix of patterns: some are descriptive phrases (ai_visibility_check, generate_llms_txt), others are domain-prefixed (nz_tender_*, polymarket_*) but lack a uniform verb_noun structure. The ask_pipeworx series diverges from the rest, and verb choices are inconsistent (compare_entities vs scan_competitor_ai_presence).

Tool Count2/5

With 34 tools, the surface is large and feels bloated. The server covers multiple distinct domains (NZ tenders, Polymarket, memory, subscriptions) that could be separate servers. Many tools are variants of the same core functionality (e.g., four ask_pipeworx variants), inflating the count without clear necessity.

Completeness3/5

For a general-purpose data query server, the tool set covers a broad range of sources (SEC, FDA, FRED, etc.) and includes CRUD for memory and subscriptions. However, obvious gaps exist: no dedicated web search tool (ask_pipeworx is for structured data), and NZ coverage is limited to tenders only. Missing update/delete for some resources (e.g., no way to modify a subscription beyond unsubscribe).

Resources