HN frontpage live — Algolia front_page tag, dwell = points/(age_h+2). Cache 10min. Top stories sorted by dwell for attention-momentum edge.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max stories, default 30 | |
| min_points | No | Min points filter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses caching (10min), data source (Algolia), and sorting logic. Being a read-only tool, no destructive behavior; but does not explicitly state it's non-destructive or mention rate limits. Adequate for a simple read tool.
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-loaded with purpose, no wasted words. Every sentence adds value.
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?
Missing description of return values (no output schema). Agent cannot know what fields each story will contain. Significant gap for such a tool.
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 coverage is 100%, so description adds little beyond what schema already provides for parameters 'limit' and 'min_points'. Dwell formula is about behavior, not parameters.
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 it retrieves Hacker News frontpage stories, using Algolia and sorted by a custom 'dwell' metric. It distinguishes from siblings by being HN-specific and mentioning the unique sorting metric.
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?
Usage context is implied ('attention-momentum edge') but no explicit guidance on when to use vs alternatives, nor any 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.
Tools cover very diverse domains (weather, FDA, legal, crypto, etc.), so cross-domain confusion is low. However, within domains there is notable overlap: multiple food recall tools (food_recall_check, food_safety), multiple weather tools (weather_current_global, weather_forecast_grid, weather_alerts, weather_bias), and several Polymarket-related tools. This can cause agent misselection.
Naming is inconsistent: some tools use verb_noun (search_arxiv, scrape, validate_agent_manifest), others use noun phrases (smart_money, space_weather, tide_data), and some are long descriptive phrases (cross_platform_arb_scan, polymarket_event_scan). No single pattern is followed, making predictions difficult.
95 tools is excessively high for any coherent purpose. The server appears to be a random aggregation of APIs with no clear scope. Such a large catalog overwhelms agents and dilutes utility; most tools could be split into specialized servers.
Although many domains are touched, each is covered only shallowly. For example, weather lacks historical data, legal lacks case details beyond court opinions, and financial lacks stock prices. There are obvious gaps like no user authentication or data persistence. The tool set feels like a collection of endpoints rather than a cohesive service.