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.
Input schema / examplesPrevious value: -[
- {
- "url": "https://www.edx.org/feed.xml"
- },
- {
- "limit": 15,
- "query": "data science",
- "url": "https://blog.coursera.org/feed/"
- }
-]New value: +[
+ {
+ "url": "https://www.edsurge.com/articles_rss"
+ },
+ {
+ "limit": 15,
+ "query": "students",
+ "url": "https://www.edsurge.com/articles_rss"
+ }
+]Input schema / examplesAdded value: +[
+ {
+ "url": "https://www.edx.org/feed.xml"
+ },
+ {
+ "limit": 15,
+ "query": "data science",
+ "url": "https://blog.coursera.org/feed/"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered externally. The description adds real value beyond that: normalization of multiple feed formats and an explicit Cloudflare-robust direct-then-proxy fallback, which tells the agent failures may be handled internally rather than surfacing as errors.
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?
Three short sentences, zero filler, front-loaded with the core action and format support before the fallback and routing notes. Every clause 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?
For a 3-parameter fetch tool with full schema coverage and full annotations, the description covers purpose, robustness behavior, and sibling routing. The only minor gap is that no output schema exists and the description doesn't describe the normalized item shape returned.
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 100%, with url, limit (1-50, default 20), and query all documented in the schema itself. The description adds no syntax or semantic detail beyond that, so the baseline 3 applies.
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?
States a specific verb (fetch, normalize) and resource (RSS/Atom/RDF feed by URL), including supported formats and the access method. It is clearly distinguishable from siblings like read_feed, subscribe, and list_feeds.
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 routes the agent: 'Use list_feeds first for curated sources,' and the CF-bypass note signals when the direct path may fail. It does not, however, contrast this with read_feed or explain when an ad-hoc URL fetch is preferable to an existing subscription.
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.