read_feedRead a curated politics & policy feed by its id (from list_feeds). Returns normalized items (title, link, published, summary). Optionally filter items by keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| feed | Yes | Curated feed id (from list_feeds). | |
| 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: +[
+ {
+ "feed": "bbc-politics"
+ },
+ {
+ "feed": "cnn-politics",
+ "limit": 10,
+ "query": "congress"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds return structure details and keyword filtering capability, which are not in 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 with no fluff. Purpose, usage, output, and optional filtering all stated concisely.
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?
Given 3 parameters, no output schema, and low complexity, the description fully explains input, output fields, and filtering. No missing information.
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 all parameters (100% coverage), so baseline 3. Description adds domain context ('politics & policy'), source hint for feed param, and clarifies query scope ('item title/summary').
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 ('Read'), resource ('curated politics & policy feed'), and specifies source ('from list_feeds') and output format ('normalized items with fields'). Distinguishes from sibling tools like 'list_feeds' and 'fetch_feed'.
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?
Description implies prerequisite (feed id from list_feeds) and scope ('politics & policy'). Does not explicitly state when not to use, but context is 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.
Most tools have distinct jobs and the descriptions are unusually explicit about routing, but there are overlapping entry points: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all sit in the same query/research space. ask_pipeworx_beta even states it currently matches ask_pipeworx exactly, which makes some boundaries genuinely ambiguous despite strong descriptions.
The set is uniformly snake_case and has useful families like polymarket_* and pipeworx_*, plus many clear verb_noun names (list_feeds, read_feed, resolve_entity, validate_claim). However, roughly a third of tools use noun-led or adjective-led names (entity_profile, deep_research, recent_alerts, polymarket_arbitrage), so the pattern is readable but mixed.
34 tools is far beyond what a 'Politics Feeds' server needs, and a large portion of the surface (npm dependency scanning, AI visibility, memory, prediction markets, LLM text generation) is unrelated to the stated purpose. This feels like a kitchen-sink monolith rather than a scoped feed server.
Within its actual implied purpose as a broad Pipeworx data-research platform, the lifecycle is well covered: discover, resolve, ask, ground, research, compare, validate, monitor, subscribe, and remember are all present. The gaps are minor—no update-subscription operation and no direct cross-feed search for the feeds named by the server—so agents can work around them.