aggregate_imported_datasetUse this paid read-only tool for deterministic grouped statistics instead of downloading rows and calculating locally. Returns bounded count, sum, average, minimum, or maximum groups with dataset provenance.
| Name | Required | Description | Default |
|---|---|---|---|
| top | No | ||
| field | No | ||
| metric | No | ||
| group_by | Yes | ||
| dataset_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds key context: it is paid, deterministic, and bounded (via the top parameter), plus mentions dataset provenance. This goes beyond the annotations and offers useful behavioral information without contradiction.
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 very concise: two sentences, front-loading the purpose and key differentiator. No fluff, every word contributes to understanding the tool's role.
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?
With 5 parameters, 2 required, and no output schema, the description is insufficient for an agent to correctly construct a call. It lacks parameter semantics, does not explain the relationship between fields, and omits return structure details. The agent would be left guessing on how to set 'field', 'top', and how the result is formatted.
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?
Schema description coverage is 0%, so the description must compensate, but it does not explain any parameter. It only lists metric types (count, sum, avg, min, max) but does not tie them to the 'metric' parameter. There is no explanation of 'dataset_id', 'group_by', 'field', or 'top'. This is a significant gap.
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 uses a specific verb ('aggregate') and resource ('imported dataset'), and clearly states the output is grouped statistics (count, sum, average, min, max) with dataset provenance, distinguishing it from local computation. It effectively communicates the tool's core function.
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?
It explicitly recommends this tool 'instead of downloading rows and calculating locally', providing a clear usage scenario. However, it does not mention when not to use it or compare with sibling tools like query_imported_dataset, which could be more explicit.
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.
Each tool maps to a distinct lifecycle stage: discovery, materialization, sampling, querying, aggregation, and payment. The main ambiguity is between search_public_datasets and search_discovered_datasets, plus some overlap between get_coverage_status and list_official_sources, but the descriptions provide enough guidance for most selections.
All tools use a consistent verb_object snake_case pattern with clear verbs: get_, list_, query_, request_, sample_, search_, and aggregate_. State-changing actions uniformly use request_, and status reads uniformly use get_.
With 14 tools, the server is well within the ideal range and each tool earns its place across the data lifecycle: discover, materialize, sample, query, aggregate, and manage access. The count feels complete without being padded.
The set covers discovery, materialization, sampling, querying, aggregation, coverage status, and paid access, with provenance embedded throughout. Minor gaps exist around the 'insights' promised in the server name and lifecycle operations like cancellation or removal, but agents can generally complete core workflows.