Skip to main content
Glama

Update RSS Feed

update_rss_feed
Destructive

Change an RSS feed's settings; only the fields sent change, and the URL cannot change. The feed then posts as the member making the change, so they need the permission of the resulting post mode, plus posts.others when someone else set the feed up. Switching postMode to SCHEDULE or PUBLISH means later items go out without further confirmation, so confirm with the user first. Ids outside the workspace return 404. Needs the posts.draft permission.

Input Schema

NameRequiredDescriptionDefault
idYesRSS feed id from list_rss_feeds or create_rss_feed
nameNoName of the feed (max 120 characters). Defaults to the feed's title
targetsNoAccounts every new item is posted to, 1 to 20. Feeds post to FACEBOOK, INSTAGRAM, THREADS, TWITTER, BLUESKY, LINKEDIN, MASTODON, TELEGRAM and GOOGLE_BUSINESS
postModeNoDRAFT creates a draft and needs posts.draft; SCHEDULE schedules the post publishDelayMinutes after the item is found and needs posts.schedule; PUBLISH publishes it right away and needs posts.publish
templateNoPost text with {title}, {link}, {description}, {author} and {feed} (max 2000 characters, default "{title}\n\n{link}"). The description, then the title, is shortened to fit each platform; the link is never cut
contentModeNoTEMPLATE fills template; AI writes one caption per platform from the article, appends the link, spends 1 AI credit per platform per item and needs ai.generate
workspaceIdNoWorkspace to act in: an id from list_workspaces. Omit to act in the workspace list_workspaces marks current. Use the same workspaceId for every call about the same workspace, since ids from one workspace (accounts, posts, uploads) do not exist in another
includeImageNoAttach the item's image, or the article's preview image (default true)
aiInstructionsNoExtra instructions for AI captions (max 1000 characters)
excludeKeywordsNoSkip items whose title or summary contains one of these (up to 50)
includeKeywordsNoPost only items whose title or summary contains one of these (up to 50)
maxPostsPerCheckNoNew items posted per check, 1 to 10 (default 3). New items are posted oldest first; the rest wait for the next check
twitterKeepLinksNoKeep links in X posts clickable (default false). Lifetime-deal plans only; each X post with a link then costs more credits. Without it, links on X go out as plain text
publishDelayMinutesNoMinutes between finding an item and its post going out, 5 to 10080. Required when postMode is SCHEDULE
checkIntervalMinutesNoMinutes between checks: 15, 30, 60 (default), 180, 360, 720 or 1440

Output Schema

NameRequiredDescriptionDefault
resultNoThe updated feed. The RSS feed: id, userId (the member it posts as, whoever last saved it), name, url, siteUrl, status (ACTIVE or PAUSED), pauseReason, lastError, postMode, publishDelayMinutes, contentMode, template, aiInstructions, includeImage, twitterKeepLinks, includeKeywords, excludeKeywords, maxPostsPerCheck, checkIntervalMinutes, targets, nextCheckAt, lastCheckedAt, lastPostedAt, createdAt and updatedAt.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Adds real context beyond the destructiveHint/openWorldHint annotations: patch semantics, the feed posting identity, permission escalation via posts.others, and the irreversible consequence of SCHEDULE/PUBLISH. The closing line 'Needs the posts.draft permission' is muddled because the schema ties posts.draft to DRAFT mode only, slightly undercutting an otherwise strong disclosure.

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?

Front-loaded with the mutation semantics, then permissions, then the dangerous side effect — a sound ordering with no filler sentences. The trailing permission sentence is redundant with the postMode semantics and is the one piece that does not earn its place.

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 15-parameter mutation with an output schema and full schema descriptions, the description covers what the schema cannot: identity/permission requirements, patch behavior, 404 scoping, and the downstream consequence of an autonomous posting mode. Nothing an agent needs before calling is missing.

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 the baseline is 3; the description still adds meaning the schema lacks, namely that omitted fields are left untouched and that the URL is not editable, plus the actor/permission dependency for each postMode. It does not explain publishDelayMinutes or the AI credit cost beyond what the schema already says.

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 and resource ('Change an RSS feed's settings') and immediately distinguishes the semantics from a full replace: partial patch, URL immutable. An agent can tell this apart from create_rss_feed, delete_rss_feed and pause_rss_feed without opening any schema.

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 clear conditional guidance for the riskiest switch ('Switching postMode to SCHEDULE or PUBLISH ... confirm with the user first') and a precondition check ('Ids outside the workspace return 404'). It stops short of naming alternatives such as pause_rss_feed to stop posting entirely, so the routing is good but not exhaustive.

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