Crawlora MCP

fever_feed

Read-only

List one city's curated Fever feed rows and the feed's own pill filter enum. Returns every row's index, title, subtype, layout and Fever category id plus the feed's complete pill list, and pill_id filters the rows while the full pill enum is still returned. Use it to discover curated category ids: Fever runs two disjoint category id spaces, and today's NYC feed carries nine category ids that fever_filters never lists (558, 566, 655, 851, 865, 871, 1033, 1070, 1109 on 2026-11-08, drifting by city and day), most of which fever_plans accepts as whatplanfilter_id (measured 566 gives 20 plans, 851 gives 9). pill_id is validated against the pills the same response returns, because the enum is only learnable from the response, so an unknown pill is an invalid-parameter error listing the accepted ids. A city_code Fever does not serve a feed for is also an invalid-parameter error naming the code rather than an empty success; take codes from fever_top_cities or fever_cities. The rows are editorial carousels, not coverage: their items are reached through fever_plans with the row's whatplanfilter_id, and carousel items are not available from this API.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "city_code": "<city_code>"
    },
    "name": "fever_feed"
  }
}

Input Schema

Name	Required	Description	Default
`pill_id`	No	Optional feed pill id, e.g. foodie or nightlife. It filters the returned rows. The accepted set is the pills array this endpoint returns; an unknown value is a typed invalid-params error listing the accepted ids (checked after the fetch, because the enum is only learnable from the response).
`city_code`	Yes	Required Fever city code, e.g. NYC. It must be a city Fever serves a feed for; an unserved code is a typed invalid-params error, not an empty feed. Take it from fever_top_cities or fever_cities.

Output Schema

Name	Required	Description	Default
`data`	Yes	The tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint and openWorldHint, and the description stays consistent while adding real behavior: pill_id filters rows but the full pill enum is still returned, validation happens after the fetch, unknown pills and unserved cities raise typed invalid-parameter errors rather than empty successes. It also flags a genuine limitation (carousel items are not available from this API). Minor deduction for not noting pagination or per-city variance limits beyond the implication that the ids drift.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The excellent lead sentence is front-loaded, but the body is dense and over-stuffed: a hardcoded date ('2026-11-08'), a full list of nine ids, and measured plan counts ('566 gives 20 plans, 851 gives 9') will drift and cost space for little selection value. Several clauses restate the same validation point twice.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read-only feed tool with a full output schema, the description covers everything an agent needs: prerequisites (valid city code source), error semantics for both parameters, the relationship to sibling tools, and the structural caveat that rows are editorial carousels rather than inventory.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, and the description partly repeats the schema's own wording about post-fetch validation. It nonetheless adds meaning the schema lacks: the two disjoint Fever category id spaces, the fact that pill_id filters rows without shrinking the returned enum, and concrete category-id examples that illustrate the parameter's domain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: 'List one city's curated Fever feed rows and the feed's own pill filter enum', and immediately names what it returns (row index, title, subtype, layout, category id, pill list). It is clearly separable from fever_filters and fever_plans, both of which are named in context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the primary use case ('Use it to discover curated category ids'), why the alternative fails ('nine category ids that fever_filters never lists'), the follow-up tool ('their items are reached through fever_plans with the row's whatplanfilter_id'), and where to get valid city codes (fever_top_cities or fever_cities). When-to-use and when-not-to-use are both covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Crawlora MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?