Skip to main content
Glama

Add feed

add_feed

Follow an RSS or Atom feed, or a site that has one: its articles start arriving in the News inbox (list_feed_items). categories group it there, e.g. ["crypto"].

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": {
      "url": "<url>"
    },
    "name": "add_feed"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe feed's or the site's address.
titleNoOptional name; the feed's own title by default.
categoriesNoCategories to group it under.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is carried structurally. The description usefully adds the concrete side effect (items land in the News inbox, categorised), but omits what happens when the same feed is added twice — a real question given idempotentHint=false — and says nothing about auth or invalid-feed errors.

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

Conciseness4/5

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

A single compact sentence, front-loaded with the verb and resource, with the effect and the example relegated to trailing clauses where they belong. No filler, though the parenthetical tool reference and example make it slightly dense for one sentence.

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

Completeness4/5

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

For a simple three-parameter creation tool with no output schema, the definition covers purpose, the URL-vs-site ambiguity, the categorisation effect and the read-side sibling. The remaining gap is duplicate/re-add behaviour, which matters given idempotentHint=false.

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

Parameters3/5

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

Schema coverage is 100%, so url, title and categories are already documented, including the 'feed's own title by default' behaviour. The description adds a small but genuine increment by explaining what categories do (group the feed in the inbox) and giving a concrete example value. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb plus resource ('Follow an RSS or Atom feed, or a site that has one') and even covers the case where a site URL is given instead of a feed URL. It also links the effect to the sibling that reads the result ('its articles start arriving in the News inbox (list_feed_items)'), so an agent can distinguish adding a subscription from reading or updating one.

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

Usage Guidelines4/5

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

Gives a clear situation for use (you want a feed's articles to start arriving in the News inbox) and names the downstream read tool, list_feed_items. It stops short of stating exclusions, such as when to prefer update_feed for an existing subscription or how to check list_feeds first to avoid duplicates.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources