dataset_filesList all files in the latest version of a Harvard Dataverse dataset identified by its DOI persistent ID (e.g. "doi:10.7910/DVN/..."), returning file names, content types, sizes, and download URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| persistent_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | Dataset files data | |
| status | No | API response status |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesPrevious value: -[
- {
- "persistent_id": "doi:10.7910/DVN/EXAMPLE"
- }
-]New value: +[
+ {
+ "persistent_id": "doi:10.7910/DVN/DUWBBU"
+ }
+]Input schema / examplesAdded value: +[
+ {
+ "persistent_id": "doi:10.7910/DVN/EXAMPLE"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Files in a dataset",
+ "properties": {
+ "data": {
+ "description": "Dataset files data",
+ "properties": {
+ "files": {
+ "description": "Array of files in dataset",
+ "items": {
+ "description": "File metadata",
+ "properties": {
+ "datafile": {
+ "description": "Datafile details",
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "status": {
+ "description": "API response status",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive). The description adds valuable behavioral context by specifying it operates on the 'latest version' of the dataset and by enumerating the returned fields (file names, content types, sizes, download URLs). This goes beyond the annotations and informs the agent of the scope.
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 ('List all files'), specifies the input, and lists the outputs. Every clause adds meaningful information without redundancy or filler.
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 read-only tool with one parameter and an output schema, the description is complete. It explains what the tool does, what input is expected, and what the agent can expect in the result. No critical information is missing for selecting and invoking the tool.
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. It explains that 'persistent_id' is a DOI persistent ID and provides a concrete example ('doi:10.7910/DVN/...'). This gives the agent enough context to format the parameter correctly, though it does not enumerate validation rules or additional constraints.
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 'List' with a clear resource ('all files in the latest version of a Harvard Dataverse dataset') and identifies the input (DOI persistent ID). It also lists the return fields, making it distinct from siblings like 'dataset' or 'dataverse' which likely handle broader metadata.
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 purpose is clear and implies when to use it (when you need file-level details of a dataset), but it does not explicitly mention alternatives or when not to use it. Sibling tools like 'dataset' and 'dataverse' are not referenced, so the agent must infer based on the resource and action.
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.
Several tool pairs have overlapping purposes, notably ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded. Also, remember/recall/forget overlap with general memory operations, and multiple polymarket tools overlap in edge detection. While the descriptions attempt to differentiate, an agent will frequently need to choose between nearly identical tools (e.g., ask_pipeworx vs. ask_pipeworx_beta).
Naming conventions are mixed: snake_case (ai_visibility_check, compare_entities), camelCase (ask_pipeworx, generate_llms_txt), and inconsistent verb usage (some start with verbs like 'search', others with nouns like 'dataset'). The polymarket and pipeworx prefixes are helpful, but overall patterns are unpredictable.
With 35 tools, this server has a very large surface area. While the domain is broad (Harvard Dataverse + Pipeworx data + Polymarket), the count feels heavy and includes many near-duplicate tools (ask_pipeworx variants) and niche tools that inflate the total. Many agents would benefit from a smaller, more focused set.
The Dataverse subset captures file metadata and search but lacks direct download/upload capabilities, causing dead ends for users who want to access actual data. The Polymarket subset lacks the ability to actually place orders despite extensive edge analysis. The Pipeworx subset covers many data queries but feels unfocused. Overall, there are notable gaps given the stated scope of the server.