get_top_storiesFetch the current live top-ranked Hacker News stories from the Firebase API. Returns up to count stories (default 10) with title, URL, score, author, comment count, and Unix timestamp.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of top stories to return (default: 10) |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | Number of top stories returned | |
| stories | Yes | Array of top stories |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds context about live data and the 'up to count' limitation, but does not disclose rate limits, authentication, or other behavioral details. 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 front-load the verb and resource, then cover the parameter behavior and return fields without redundant words. The description is efficient and well-structured.
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?
This is a simple read-only tool with one optional parameter, rich annotations, and an output schema. The description provides the essential context about live data, count limits, and return fields, leaving no critical gaps.
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?
The schema covers the single `count` parameter with its default, but the description adds the crucial clarification that the tool returns 'up to `count` stories', implying it may return fewer. This goes beyond the schema's generic 'Number of top stories to return'.
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 tool fetches 'current live top-ranked Hacker News stories from the Firebase API', using a specific verb and resource. It distinguishes from siblings like get_stories by mentioning 'top-ranked' and 'live', but does not explicitly compare or contrast with alternatives.
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 explicit when-to-use or alternative guidance is provided. The description implies it should be used for retrieving top Hacker News stories, but does not mention exclusions or direct users to sibling tools like get_hn_comments or search_hn for other needs.
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 overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are nearly identical, and deep_research also overlaps with them. The Polymarket tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) also have fuzzy boundaries. An agent could easily pick the wrong meta-tool or duplicate functionality.
All names are snake_case, but the pattern is mixed: some are verb_noun (get_item, list_subscriptions, resolve_entity), some are noun_noun (entity_profile, pipeworx_feedback, polymarket_edges), some are adjective_noun (deep_research, recent_alerts), and a few are single verbs (forget, recall, remember, subscribe). This is readable but not a consistent convention.
With 36 tools, this is far too many for a server named 'hackernews'. The bulk of the tools concern Pipeworx data research, prediction markets, memory, and subscriptions — unrelated to the server's apparent purpose. Many of these could be split into separate servers, and the HN-specific functionality would be better served by a focused set of ~5-8 tools.
For the Hacker News domain implied by the server name, the surface is incomplete: there are read-only tools (search, top stories, item/comments) but no write functionality (submit, comment, vote) and no user profile access. The broader data-research capabilities are fairly comprehensive, but that does not rescue the server's coherence given its stated name.