fetch_feedFetch and normalize any RSS / Atom / RDF feed by URL. CF-robust: fetches directly and falls back to a proxy if the source blocks the gateway. Use list_feeds first for curated sources.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Feed URL, e.g. "https://news.ycombinator.com/rss". | |
| limit | No | Max items (1-50, default 20). | |
| query | No | Keyword filter over item title/summary. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "url": "https://news.ycombinator.com/rss"
+ },
+ {
+ "limit": 15,
+ "query": "physics",
+ "url": "https://feeds.nature.com/nature/rss/current"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive. Description adds useful context: CF-robust with direct fetch and proxy fallback, and normalization. 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?
Two sentences, each serving a distinct purpose: first defines core action, second adds robustness and usage guidance. No wasted words.
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?
Tool has no output schema; description does not explain return format. However, it does specify normalization and gives examples in schema. For a fetch tool, mostly complete, but lacks explicit return value description.
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 covers 100% of parameters with clear descriptions. Description does not add extra meaning beyond schema, but also does not mislead. Baseline score for full schema 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?
Description clearly states verb ('Fetch and normalize'), resource ('any RSS / Atom / RDF feed'), and parameter ('by URL'). It also distinguishes from sibling 'list_feeds' by advising to use that first for curated sources.
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?
Explicitly guides to use 'list_feeds' first for curated sources, providing a clear alternative. Also mentions CF-robust fallback behavior, but does not give explicit exclusions or prerequisites.
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 tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta (currently identical), ask_pipeworx_grounded, deep_research, and validate_claim all route questions to data, while the six polymarket_* tools blur edge-finding, arbitrage, and fill-risk. ai_visibility_check and scan_competitor_ai_presence also overlap, with the latter wrapping the former.
All names are snake_case and readable, with clear families like polymarket_*, ask_pipeworx*, and list_*. However, conventions mix verb-first names (resolve_entity, read_feed) with noun-first names (entity_profile, pipeworx_trending, recent_alerts, deep_research), so no single pattern dominates.
34 tools is heavy for any server, but the real issue is scope sprawl: science feeds, a universal data router, prediction-market analysis, memory, subscriptions, AI-visibility checks, and npm scanning each form a mini-server. The count is not defensible for the 'Science Feeds' purpose and would be better split into several focused servers.
There is no coherent domain to assess completeness against—'Science Feeds' describes only 3 of 34 tools. Individual clusters are partially complete (subscriptions have subscribe/list/unsubscribe/recent_alerts, memory has remember/recall/forget), but the overall surface is a grab-bag of features from unrelated products, with obvious gaps in each (e.g., no way to update a subscription, no direct access to specific data packs except through the router).