datasetsSearch the New Jersey Open Data catalog of open datasets by keyword. Returns each dataset's resource_id, name, description, category and update date — pass the resource_id to query/metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max datasets (1-100, default 20). | |
| query | No | Keyword to search dataset titles/descriptions (e.g. "budget", "crime", "health"). | |
| offset | No | Pagination offset. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds return structure (resource_id, name, description, category, update date) and the cross-tool hint about query/metadata, providing useful context beyond 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?
Two sentences: first states action and parameters, second explains returns and next step. No wasted words, 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?
Given no output schema, the description adequately explains return fields (resource_id, name, description, category, update date). All parameters are documented, safety is clear from annotations. Complete enough for agent to use correctly.
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% with descriptions for all three parameters. Description adds no new semantics beyond the schema; it mentions 'keyword' but the schema already describes query as 'Keyword to search...'. Baseline of 3 applies.
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?
Description clearly states verb 'search' and resource 'New Jersey Open Data catalog'. It lists return fields. While it doesn't explicitly distinguish from siblings, the specific domain (NJ Open Data) helps differentiation.
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?
Description says to search by keyword but gives no guidance on when to use this tool vs alternatives like 'query' or 'search_within'. It does hint at a follow-up action ('pass the resource_id to query/metadata').
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 distinct purposes, but some overlap exists between ask_pipeworx, ask_pipeworx_grounded, and deep_research, which all query Pipeworx data in different modes. However, their descriptions clearly differentiate them. Similarly, memory and subscription tools are separate. Overall, an agent can distinguish tools with moderate effort.
Tool names mostly follow verb_noun pattern with snake_case, such as ask_pipeworx, compare_entities, generate_llms_txt. However, a few tools like 'datasets', 'metadata', and 'query' are single nouns, breaking the pattern. Overall, naming is consistent enough for an agent to predict behavior.
33 tools is above the typical range for an MCP server, but the server covers a wide domain (SEC, FRED, FDA, prediction markets, etc.) with specialized tools. The count is borderline heavy but justifiable given the scope. Some tools like memory and subscription management add to the count but serve necessary auxiliary functions.
The tool surface is comprehensive for its intended domain of structured data querying and analysis. It covers data retrieval, entity resolution, comparison, news, subscriptions, and memory. Minor gaps include dependency scanning only for npm and lack of direct web search, but meta-tools like ask_pipeworx fill many needs. Overall, it supports common workflows well.