Skip to main content
Glama
Upload-Post

Upload-Post

Official

Manage webhook settings

manage_webhook_settings
Destructive

Configure, preview, test, or remove account and per-profile webhook URLs and events for Upload-Post, so you can control where upload and social notifications are sent.

Instructions

The account webhook (one URL that gets the account's events) and per-profile webhooks (a profile sending its events to its own URL instead). The signing secret is never returned: responses only say webhook_secret_set, and the user sees or rotates it in the dashboard. get_account: current notification settings (channels {webhook, telegram}, webhook_url, webhook_events, telegram_chat_id). set_account: change only the fields sent (webhook_url, webhook_events, channels, telegram_chat_id); the first URL saved creates the signing secret. remove_account: clears webhook_url, webhook_events and the secret and turns the webhook channel off (webhook subscriptions keep working). test_account: sends a sample upload_completed through the configured channels (params: platform, media_type, title, caption, profile_username), logged as a test delivery. get_profile / set_profile (webhook_url; webhook_events {event: true|false}, omitted = every event, null = back to every event) / remove_profile (its events go back to the account webhook): need profile_username. webhook_events names: upload_completed, social_account_connected, social_account_disconnected, social_account_reauth_required, dm_received, comment_received and the others listed in create_webhook_subscription. Team members cannot change where the owner's events go (403). Needs the user's approval: call it first without confirmed to get a preview (nothing is sent), show the user exactly what will go out, and repeat the call with confirmed: true only after they approve.

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": {
      "action": "<action>"
    },
    "name": "manage_webhook_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
paramsNoOther fields with the API's names: set_account channels {webhook: bool, telegram: bool} and telegram_chat_id; test_account platform, media_type, title, caption, profile_username.
confirmedNoSet to true only after the user has seen the preview this tool returns without it and approved it. Without it nothing is sent.
webhook_urlNoset_account / set_profile: public https URL that receives the events.
webhook_eventsNoset_account: list of event names (omitted = every event). set_profile: {event: true|false}, or null to go back to every event.
profile_usernameNoget_profile / set_profile / remove_profile: the Upload-Post profile.

Output Schema

NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.26.5

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the destructiveHint annotation, it discloses that the signing secret is never returned and only surfaced as `webhook_secret_set`, that the first saved URL creates the secret, that remove_account clears the secret and disables the channel while existing webhook subscriptions keep working, that test deliveries are logged, and that team members get a 403 on owner events. These are exactly the side effects and permission boundaries an agent needs before mutating webhook configuration.

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?

Dense but nearly every clause carries actionable information; the approval protocol is saved for the end where it reads as a precondition. Minor waste exists, such as restating the test_account parameter list already present in the `params` schema description, and the whole thing is delivered as one undifferentiated prose block rather than grouped per action.

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?

An output schema exists, so return values need not be explained. Across seven actions, a nested `params` object, secret-handling rules, permission constraints and an approval flow, nothing material is left for the agent to guess.

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 already 83%, so the baseline is 3; the description adds per-action semantics, notably that webhook_events is a list for set_account but an event->bool map for set_profile, with omitted meaning every event and null resetting to every event. It also clarifies which `params` fields belong to set_account versus test_account and that profile_username is required for all profile actions, though some of this overlaps the schema text.

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?

The description names the resource (account-level and per-profile webhooks) and enumerates every operation the action enum supports (get/set/remove/test for account, get/set/remove for profile), each with a one-line statement of what it does. An agent can distinguish this from create_webhook_subscription, which is explicitly cited as the source of the valid event names.

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?

It gives per-action usage context (remove_profile returns events to the account webhook; set_account only changes fields sent; test_account logs a test delivery) plus an explicit two-step approval protocol: call without `confirmed` to preview, then repeat with `confirmed: true` after the user approves. It also states the 403 constraint for team members. It stops short of explicitly ruling out sibling tools like create_webhook_subscription or test_webhook_subscription, so not a full 5.

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

Deploy Server

Other Tools