get-dataset-itemsRead result rows from a caller-owned Apify dataset, with bounded pagination and optional field selection.
| Name | Required | Description | Default |
|---|---|---|---|
| desc | No | ||
| omit | No | ||
| clean | No | ||
| limit | No | ||
| fields | No | ||
| offset | No | ||
| flatten | No | ||
| datasetId | Yes | Dataset ID or username~dataset-name. |
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 useful context beyond annotations: the dataset must be caller-owned, pagination is bounded, and field selection is optional. This helps an agent understand scope and limitations without contradicting the 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?
A single sentence with no filler, front-loaded with the core action and resource. Every phrase carries meaning: 'Read', 'caller-owned', 'bounded pagination', and 'optional field selection' all add useful information without 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?
The tool has 8 parameters, very low schema coverage, and no output schema, yet the description is only one sentence. It does not explain parameter semantics, return shape, pagination behavior, or how field selection/omission works. This is not complete enough for a tool of this complexity.
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 only 13%, with only datasetId described. The description mentions 'bounded pagination' and 'optional field selection' but does not explain the meanings of limit, offset, fields, omit, flatten, clean, or desc. With this low coverage, the description needed to compensate and did not.
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 states a specific verb ('Read'), a specific resource ('result rows from a caller-owned Apify dataset'), and two distinguishing capabilities ('bounded pagination and optional field selection'). It clearly differentiates this tool from siblings like get-key-value-store-record and get-actor-run, which read different resource types.
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?
The description gives clear context: this tool is for reading result rows from a dataset the caller owns. It does not explicitly name alternatives or exclusion conditions, but the caller-owned and dataset-row scoping are enough to guide an agent toward correct use versus the sibling 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.
The domain-specific tools are clearly separated by record type, with explicit cross-references that reduce confusion between similar categories like Texas vs. multistate childcare or STR permits vs. Florida DBPR lodging. The main ambiguity is the broad evidence-gateway tool, which overlaps with several specialized query tools and could be selected instead of the more precise one.
The domain tools follow a consistent civicdataforge-- prefix pattern, and the Apify utilities follow a get-/abort- verb pattern, making the overall set readable. Minor deviations include the awkward civicdataforge--civicdataforge-evidence-gateway duplication and the mix between noun-style domain tools and verb-style utility tools.
With 14 tools, the set is well-scoped: ten specialized public-record query tools plus four Apify lifecycle/data-access utilities. Each tool has a distinct role, and the count is appropriate for the breadth of supported public records without feeling bloated.
The tool surface covers a broad range of public-record evidence categories and provides the necessary run, dataset, and key-value-store operations for working with results. Minor gaps include a lack of discovery tools for listing supported jurisdictions/sources and no general-purpose search across all record types, but the core evidence workflows are well covered.