article_filesList downloadable files attached to a Figshare article by numeric id (optionally a specific version). Returns file names, sizes, MIME types, and direct download URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| version | No |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | Number of items returned. | |
| items | Yes | Files in an article |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "id": 1234567
+ },
+ {
+ "id": 1234567,
+ "version": 3
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "count": {
+ "description": "Number of items returned.",
+ "type": "integer"
+ },
+ "items": {
+ "description": "Files in an article",
+ "items": {
+ "properties": {
+ "download_url": {
+ "description": "File download URL",
+ "type": "string"
+ },
+ "id": {
+ "description": "File ID",
+ "type": "number"
+ },
+ "is_link": {
+ "description": "Whether file is an external link",
+ "type": "boolean"
+ },
+ "name": {
+ "description": "File name",
+ "type": "string"
+ },
+ "size": {
+ "description": "File size in bytes",
+ "type": "number"
+ },
+ "supplied_md5": {
+ "description": "MD5 checksum",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "items",
+ "count"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive behavior. The description adds valuable context about the return payload (file names, sizes, MIME types, direct download URLs) and the optional version parameter, going beyond what annotations provide. No contradiction with 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?
The description is a single, front-loaded sentence that directly states the action, resource, and return values. No filler or redundant information; every element earns its place.
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 is simple with two parameters and an output schema. The description covers purpose, key input, and return fields, which is sufficient for a straightforward list operation. It omits edge-case behaviors like empty results or pagination, but the annotations and output schema mitigate the need for further detail.
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 clarifies 'id' as numeric and mentions 'version' as optional, but does not elaborate on version semantics (e.g., version of the article) or provide additional parameter details beyond the schema examples. Basic compensation, not comprehensive.
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 clearly states the tool's function: listing downloadable files attached to a specific Figshare article, identified by numeric id, with an optional version. It specifies the action, resource, and scope, and implicitly distinguishes from sibling tools like 'article' and 'articles' by focusing on files.
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 implies usage context (retrieving article attachments) and identifies the key input (numeric id) and optional version. However, it does not explicitly compare with alternative tools or provide exclusions, so it falls short of full guidance but is still clear.
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.
Multiple tools overlap heavily: ask_pipeworx and ask_pipeworx_beta are documented as currently identical, ask_pipeworx_grounded/deep_research route the same class of questions, and the six polymarket_* tools plus bet_research form a confusing cluster. Some clusters (Figshare fetch/search, memory, subscriptions) are distinct, but overall boundaries are frequently unclear.
Names are uniformly lowercase snake_case and mostly follow a predictable verb_noun pattern (ask_pipeworx, list_subscriptions, resolve_entity, scan_dependency). The main inconsistency is the mix of bare-noun Figshare resource names (article, articles, collection, collections) with verb-phrase tool names.
38 tools is well above the comfortable scope for a coherent server, especially one named Figshare. Most of the surface is unrelated to Figshare, bundling Pipeworx research, Polymarket analysis, memory, subscriptions, AI visibility, and npm checks into a single connection.
The Figshare read-side is reasonably covered (search, article metadata, files, collections, categories, licenses), but there are no create/update/delete or account/upload operations. The broader advertised surface is a grab bag with no clear domain boundary, and several subdomains are shallow while prediction markets are over-represented.