searchFull-text search across Commons.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 1-500 (default 20). | |
| query | Yes | ||
| offset | No | ||
| namespace | No | 0 (article) | 6 (file, default) | 14 (category) |
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| batchcomplete | No | Whether the query is complete |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "query": "Eiffel Tower"
+ },
+ {
+ "limit": 50,
+ "namespace": 6,
+ "query": "butterfly species"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "batchcomplete": {
+ "description": "Whether the query is complete",
+ "type": "boolean"
+ },
+ "query": {
+ "properties": {
+ "search": {
+ "description": "Array of search results",
+ "items": {
+ "properties": {
+ "ns": {
+ "description": "Namespace ID",
+ "type": "number"
+ },
+ "pageid": {
+ "description": "Page ID",
+ "type": "number"
+ },
+ "size": {
+ "description": "Page size in bytes",
+ "type": "number"
+ },
+ "snippet": {
+ "description": "Search result snippet",
+ "type": "string"
+ },
+ "timestamp": {
+ "description": "Last edit timestamp",
+ "type": "string"
+ },
+ "title": {
+ "description": "Page title",
+ "type": "string"
+ },
+ "wordcount": {
+ "description": "Word count",
+ "type": "number"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "search-continue": {
+ "description": "Continuation offset for pagination",
+ "type": "number"
+ }
+ },
+ "type": "object"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds 'full-text search' but no further behavioral traits such as rate limits or result details.
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 clear sentence front-loaded with the action. It is concise but lacks informative depth necessary for effective tool selection.
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 4 parameters, an output schema, and many sibling tools, the description is insufficient. It omits pagination behavior, namespace usage, result format, and differentiation from similar search tools.
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 50% (descriptions for limit and namespace only). The description does not add meaning for query or offset parameters, failing to compensate for the low coverage.
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 verb 'search' and the resource 'Commons', indicating full-text search. However, it does not distinguish from sibling tools like 'search_within' or 'deep_research', which have overlapping purposes.
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 on when to use this tool versus alternatives such as 'search_within' or 'category_members'. The description provides no context for appropriate usage scenarios.
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.