search_public_datasetsUse this free tool first when an agent needs official US federal data but does not yet know the dataset ID. Searches normalized catalog metadata and returns matching datasets with provenance; it does not query dataset rows.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Plain-language topic, agency, or dataset keywords, such as employment, schools, or air quality. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as readOnly, idempotent, and non-destructive; the description adds meaningful behavioral context by noting it is free, searches normalized metadata, returns provenance, and avoids querying dataset rows. This usefully frames cost and scope beyond what annotations state.
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?
Two tightly written sentences that front-load the most important usage guidance and follow with scope boundaries. Every sentence adds value, and there is no repetition of schema or annotation details.
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 single-parameter, read-only search tool, the description is complete: it explains when to use it, what it searches, what it does not do, and what kind of results are returned. The existing annotations cover safety semantics, so no further behavioral disclosure is needed.
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 coverage is 100%, and the schema already describes the query parameter well with examples. The description reinforces plain-language usage but does not materially add meaning beyond the schema. Baseline 3 is appropriate.
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?
States a specific verb ('searches') and resource ('normalized catalog metadata') and clearly distinguishes itself from row-level query tools. The phrase 'does not query dataset rows' removes ambiguity about what kind of search this performs.
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?
Gives explicit situational guidance: use first when an agent needs official US federal data but does not yet know the dataset ID. It also conveys a boundary by stating that it does not query dataset rows, implying row-level tools should be used instead. It does not name a specific alternative, but the context is strong enough.
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 target clearly distinct actions and states, such as searching, sampling, querying, materializing, or requesting paid access. The main ambiguity is between search_public_datasets and search_discovered_datasets, which both search catalog metadata and differ mainly in scope and materialization-state reporting.
All tool names follow a consistent snake_case verb_noun pattern, using clear verbs like list, search, sample, query, request, get, and aggregate. The naming makes the action and subject predictable across the entire set.
With 14 tools, the server covers distinct stages of a coherent workflow: discovery, materialization, status polling, sampling, querying, aggregation, coverage checking, and paid access. Each tool addresses a meaningful step without excessive redundancy.
The tool surface covers the full discovery-to-paid-query lifecycle for imported government datasets and includes dedicated Federal Register access. Minor gaps exist, such as no explicit dataset-detail or payment-status tool, but agents can work around these using list/search and request_paid_access.