discover_feedsGiven a site's normal URL, return the feeds it declares in its HTML head, each with title and type. Use when you know a site publishes updates but not where its feed lives. If the page declares none, conventional locations are suggested and clearly marked as guesses that may 404. Costs $0.005 USDC per call via x402 on Base.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The site's page URL, e.g. 'https://blog.rust-lang.org'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral burden and does well. It discloses the fallback behavior (suggesting conventional locations) and flags those guesses as may-404, plus the exact cost and payment mechanism. It doesn't cover failure modes or exact output shape, but the key behaviors are transparent.
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 sentences with no filler. The primary action is first, the usage condition second, the fallback and cost information last. Each sentence 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 tool with one well-documented parameter and no output schema, the description provides everything needed: input semantics, expected return content, fallback behavior, and cost. An agent can call this correctly without additional context.
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% for the single url parameter, and the description adds a slight clarification ('site's normal URL'). Since the schema already documents the parameter sufficiently, the baseline 3 is appropriate.
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 states a specific verb ('discover') and resource (feeds declared by a site's HTML head), and clearly distinguishes it from siblings like read_feed by focusing on locating feeds rather than consuming them. The title 'Find the feed for a website' reinforces this precise scope.
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 states when to use the tool: 'Use when you know a site publishes updates but not where its feed lives.' It does not explicitly name alternative tools or when not to use it, but the usage condition is clear enough for an agent to route to this tool versus siblings.
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.
Each tool has a clearly distinct role: discover_feeds locates feed URLs, read_feed consumes and normalizes them, demand_report surfaces aggregate market demand, and request_data handles individual data-looking requests. Even the two marketplace-related tools are separated by scale and purpose.
All tool names follow the same verb_noun snake_case pattern: discover_feeds, read_feed, request_data, demand_report. The style is uniform and each name accurately suggests its action.
Four tools is a well-scoped count for this server's purpose: two feed operations and two data-marketplace operations. Each tool earns its place without redundancy or bloat.
The core feed workflow is complete: discover where a feed lives, then read and normalize it with optional since-based polling. The demand-report and request-data tools round out the marketplace side without leaving obvious dead ends.