search_datasetsSearch curated ABS, RBA, and APRA economic datasets.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Discovery query text. | |
| source | No | Optional source filter. Use abs for Australian Bureau of Statistics, rba for Reserve Bank of Australia, or apra for Australian Prudential Regulation Authority. |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes | Ranked ABS, RBA, and APRA catalogue search results. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds minimal context like 'curated' suggesting a limited dataset set, but doesn't describe result behavior, pagination, or matching semantics. No contradiction 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the action ('Search') and scope ('curated ABS, RBA, and APRA economic datasets'). Every word earns its place with no redundancy.
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 simple search tool, the description is largely sufficient given that annotations cover safety and the output schema covers return values. However, it omits details about search behavior (e.g., exact vs. fuzzy matching) and could briefly indicate when to prefer this over list_catalogue, which would improve completeness.
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 input schema has 100% description coverage for both parameters, with query described as 'Discovery query text' and source explaining each enum value. The description adds no additional parameter semantics beyond what the schema already provides.
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 clearly states the tool searches curated economic datasets from ABS, RBA, and APRA, using a specific verb and resource scope. While it doesn't explicitly contrast with sibling tools, the 'Search' verb and the named sources distinguish it sufficiently from retrieval tools like get_abs_data or list_catalogue.
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?
There is no explicit guidance on when to use this tool versus alternatives. The description implies it is for searching datasets by query, but does not mention when to use list_catalogue or how it differs from specific data retrieval tools.
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.
Most tools have clear source or function boundaries (ABS, RBA, APRA, derived series, curated concepts, discovery). However, get_derived_series and get_economic_series both retrieve time-series data and could be confused; list_catalogue and search_datasets also overlap in discovery. The descriptions help, but these pairs require careful reading.
All tools follow a consistent lowercase verb_noun pattern with underscores (describe_, get_, list_, search_). Verbs are used predictably: get for retrieval, list for enumeration, search for discovery. No mixed conventions or camelCase.
14 tools is on the higher end but appropriate for a multi-source economic data API covering ABS, RBA, and APRA. The inclusion of a deprecated alias (list_rba_tables) adds slight redundancy, but the overall count is justified by distinct operations.
The surface covers discovery (search_datasets, list_catalogue), metadata (describe_dataset, structure), retrieval (source-specific and curated), and convenience wrappers (latest/top observations). Minor gaps include lack of a unified structure tool for RBA/APRA and no bulk download option, but core read-only workflows are well covered.