category_membersItems in a Commons category.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| category | Yes | e.g. "Category:Cats" | |
| cmcontinue | No |
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| continue | No | Pagination continuation data | |
| batchcomplete | No | Whether the query is complete |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "category": "Category:Cats"
+ },
+ {
+ "category": "Category:Photographs of flowers",
+ "limit": 100
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "batchcomplete": {
+ "description": "Whether the query is complete",
+ "type": "boolean"
+ },
+ "continue": {
+ "description": "Pagination continuation data",
+ "properties": {
+ "cmcontinue": {
+ "description": "Continuation token for next batch",
+ "type": "string"
+ },
+ "continue": {
+ "description": "Continue value",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "query": {
+ "properties": {
+ "categorymembers": {
+ "description": "Array of category members",
+ "items": {
+ "properties": {
+ "ns": {
+ "description": "Member namespace ID",
+ "type": "number"
+ },
+ "pageid": {
+ "description": "Member page ID",
+ "type": "number"
+ },
+ "title": {
+ "description": "Member title",
+ "type": "string"
+ },
+ "type": {
+ "description": "Type of category member",
+ "enum": [
+ "page",
+ "file",
+ "subcat"
+ ],
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and idempotentHint=true, so the description adds no behavioral context. It fails to mention pagination (cmcontinue), rate limits, or output structure, missing an opportunity to enhance transparency.
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 under-specified to the point of being unhelpful. While short, it fails to convey essential information, making it ineffective rather than concise.
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?
With 3 parameters and an output schema, the description should clarify what the tool returns and how pagination works. It does not, leaving significant gaps for an AI agent to infer correct usage.
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 33% (only category has a description). The description does not explain the purpose of limit, cmcontinue, or how they interact. It adds no value beyond the schema's minimal documentation.
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 'Items in a Commons category.' is a noun phrase and does not specify the action (e.g., list, retrieve). It vaguely hints at the resource but lacks a clear verb, making it insufficient for an agent to understand what the tool does.
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?
No guidance is provided on when to use this tool versus alternatives. Sibling tools like search or entity_profile could overlap, but the description does not differentiate or suggest appropriate contexts.
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 have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical routers, and the six polymarket_* tools plus bet_research all cover prediction-market analysis with blurry boundaries. The server name 'Commons Wikimedia' also clashes with 30+ Pipeworx tools, making the overall purpose ambiguous. Only the handful of Commons-specific tools (category_members, file_info, file_revisions, random_image, search) are clearly distinct.
All names are lowercase snake_case and many follow a noun_phrase pattern (entity_profile, polymarket_edges, recent_changes), but verb styles are inconsistent: some are bare verbs (search, recall, subscribe), some are verb_noun (generate_llms_txt, resolve_entity, validate_claim), and several are noun-only (category_members, file_info, pipeworx_feedback). The style is readable but not predictable, mixing action-first and object-first conventions.
36 tools is far too many for a server ostensibly named 'Commons Wikimedia' — the vast majority belong to the Pipeworx data platform, not Wikimedia Commons. The count exceeds the 25-tool threshold for 'too many,' and the scope mismatch between the server name and the actual toolset makes the abundance feel even more unjustified.
For 'Commons Wikimedia,' the surface is severely incomplete: there is no upload, no category tree navigation, no file download, and no structured search beyond full-text. For the Pipeworx domain, coverage is broad but indirect — most data access funnels through aggregate/meta tools (ask_pipeworx, entity_profile, deep_research) rather than direct per-source tools, leaving gaps for granular lookups and leaving the Commons tools stranded with no real integration.