Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Manage Linkedin Invite Queue

manage_linkedin_invite_queue
Destructive

Bulk operations (status, approve-all, cancel_all) act on the current agent's queue when run inside an agent, and across the whole account from account-level chat — except a bulk cancel_all or approve-all, which from account-level chat is rejected unless agent_id names the campaign, so it can't hit every campaign at once. Targeting one person by target_provider_id reaches them in any agent. Pacing / next_scheduled / daily usage stay account-wide (the LinkedIn rate limit is per-account). Dict with action result and current queue status

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesOne of: - 'status': Get full queue details (pending/sent/failed items with names and times). The `pending_items` / `pending_approval_items` / `failed_items` lists cap at 50 each, each with a matching `*_truncated` flag — when a list's flag is True, more rows exist past this page; pass `offset` (offset += 50) to read them. Each `failed_items` row carries `last_error`, the reason that send failed — read it to answer "why wasn't X sent?". `pending_approval_items` rows also carry `last_error` when the row was held for a reason beyond plain approval gating (e.g. the resolver's name-mismatch hold). Queued post comments and reactions carry `post_url` and a `post_text` excerpt of the post the action targets, so you can tell which post a queued comment is on; `post_text_truncated` True means the target post ran longer than the excerpt shown. All four lists share one field shape; a `resolving_items` row (profile not yet resolved) has a blank `target_provider_id` and its `message` is the copy that will send once it resolves — edit or cancel it by its `target_identifier`. Every `pending_items` / `resolving_items` row carries `projected_send_day` + `projected_send_time` (a resolving row's is its projected lookup time, or its projected send time once it's a resolve-then-send) and a `queue_position` — the row's place in the one ordered lookup+send timeline, so the two lists interleave into what actually fires next. The top-level `cancelled_by_kind` maps each cancel cause to its count (`recipient_replied`, `task_deleted`, `auto_shelved`, …; pre-taxonomy rows under `unknown`) — read it to answer "how much outreach was cancelled, and why?". - 'update': Update a queued item's message text. Name the item by target_provider_id (a pending row's pid) OR, for a resolving row that has no pid yet, by target_identifier (its URL/slug, shown on the row). Use this to edit a queued message — including on resolving rows, which still hold the message that will send once their profile resolves. When a target has more than one queued action — a post with both a comment and a reaction, or a person with a connection request and a follow — also pass action_type to name which one to edit. - 'approve': Send authorization belongs to the user, so this action needs a message that arrived after the drafts were queued and explicitly says to approve or send them. A message from before the drafts existed cannot authorize them — a request to review them, to approve them later, or to be able to approve from chat means: report that the queue is awaiting approval and end your turn; the user's next message decides. Once authorized, this moves pending_approval items to 'pending'; they then send in queue order at your account's pace. If target_provider_id is given, approve only that item. Otherwise approve ALL pending_approval items (optionally filtered by action_type). Only touches items already awaiting approval — it does NOT run pending profile lookups or pre-approve resolving rows (those aren't in the approvals UI, so nobody has reviewed them; they resolve on their own schedule and, if the user's settings gate the action, surface for approval once resolved). From account-level chat an approve-all is rejected unless agent_id names the campaign — it must not fire every campaign's drafts into sending at once. - 'cancel': Cancel a queued item. Pass target_provider_id to cancel that one person or post — every queued action for them — or target_identifier to cancel a resolving row that has no pid yet. To cancel the ENTIRE pending queue — which drops drafts the user already approved — you must pass cancel_all=True; an unscoped cancel without it is rejected (an action_type or node_id filter alone is still a bulk cancel and also needs cancel_all=True). Narrow a cancel_all to one flow stage with node_id (e.g. restart only the m2 messages without touching m3) — the only way to separate two stages that share an action_type. From account-level chat a cancel_all is rejected unless agent_id names the campaign to cancel — it must not clear every campaign's queue at once. - 'pause': Pause the queue (stops sending, keeps items queued). Pass resume_at to schedule an automatic resume ("pause while I'm on vacation, resume July 20"); without it the pause is indefinite and only an explicit 'resume' restarts sending. - 'resume': Resume the queue (pending items drain in queue order at your account's pace)
offsetNoFor 'status' only — skip this many items in each queued list before returning the next 50. Use it to page through a queue larger than 50 (offset=50 for items 51-100, etc.).
messageNoFor 'update' — new message text. 300 chars max for connection requests.
node_idNoFor 'cancel' only — narrow a cancel_all to the queue rows on one flow node (the row's flow stage, e.g. 'm1', 'm2'), parallel to action_type. action_type is the send mechanism (connection_request / message / inmail / ...), not the stage, so every message stage shares action_type='message' — node_id is the only handle that isolates one (m1 and m2 are both action_type='message', so only node_id restarts m1 without touching m2). Still a bulk cancel — needs cancel_all=True, not a substitute for it.
agent_idNoFor 'cancel' and 'approve' — scope a bulk cancel_all / approve-all to one campaign's queue. Required from account-level chat (no active agent), where an unscoped bulk cancel or approve is rejected; call list_agents to get the id.
resume_atNoFor 'pause' — ISO datetime when sending should automatically resume. Must be in the future. A naive datetime is interpreted in the user's timezone. Use resolve_date first for natural language ("July 20", "in 2 weeks").
cancel_allNoFor 'cancel' only — confirm a queue-wide cancel when no target_provider_id is given. Guards against silently tearing down the whole campaign.
action_typeNoThe kind of queued action to target, as shown on each queue row in the 'status' result (e.g. 'comment', 'reaction', 'connection_request', 'follow'). For 'update', pass it when a target carries more than one queued action so the right row is chosen. For 'approve' and 'cancel', it narrows the bulk operation to one kind — a bare target_provider_id on 'cancel' cancels every queued action for that person or post. Not a substitute for cancel_all.
as_teammateNoAct on a consented teammate's queue instead of your own — pass their email. Covers approve / cancel / update / status; pause and resume (account-wide controls) are not available on a teammate's behalf. A bulk approve-all / cancel_all must name one of the teammate's campaigns via agent_id. Gated on that teammate's act-on-behalf setting; a teammate who hasn't granted it is rejected. Omit for your own.
target_identifierNoFor 'update' and 'cancel' of a resolving row (profile not yet resolved, blank target_provider_id) — the row's URL/slug, shown on the row in the 'status' result. Ignored when target_provider_id is set.
target_provider_idNoFor 'update' and 'cancel' — the person's pid or post URN to target. A resolving row has no pid yet — target it by target_identifier instead. For 'cancel', leave empty (with cancel_all=True) to cancel all pending items.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"One of:\n- 'status': Get full queue details (pending/sent/failed items with names and times).\n  The `pending_items` / `pending_approval_items` / `failed_items` lists cap at 50\n  each, each with a matching `*_truncated` flag — when a list's flag is True, more\n  rows exist past this page; pass `offset` (offset += 50) to read them. Each\n  `failed_items` row carries `last_error`, the reason that send failed — read it to\n  answer \"why wasn't X sent?\". `pending_approval_items` rows also carry `last_error`\n  when the row was held for a reason beyond plain approval gating (e.g. the\n  resolver's name-mismatch hold). Queued post comments and reactions carry `post_url`\n  and a `post_text` excerpt of the post the action targets, so you can tell which\n  post a queued comment is on; `post_text_truncated` True means the target post ran\n  longer than the excerpt shown. All four lists share one field shape; a\n  `resolving_items` row (profile not yet resolved) has a blank `target_provider_id`\n  and its `message` is the copy that will send once it resolves — edit or cancel it\n  by its `target_identifier`. Every `pending_items` / `resolving_items` row carries\n  `projected_send_day` + `projected_send_time` (a resolving row's is its projected\n  lookup time, or its projected send time once it's a resolve-then-send) and a\n  `queue_position` — the row's place in the one ordered lookup+send timeline, so the\n  two lists interleave into what actually fires next. The top-level `cancelled_by_kind` maps each cancel\n  cause to its count (`recipient_replied`, `task_deleted`, `auto_shelved`, …;\n  pre-taxonomy rows under `unknown`) — read it to answer \"how much outreach was\n  cancelled, and why?\".\n- 'update': Update a queued item's message text. Name the item by\n  target_provider_id (a pending row's pid) OR, for a resolving row that has no\n  pid yet, by target_identifier (its URL/slug, shown on the row). Use this to\n  edit a queued message — including on resolving rows, which still hold the\n  message that will send once their profile resolves. When a target has more\n  than one queued action — a post with both a comment and a reaction, or a\n  person with a connection request and a follow — also pass action_type to name\n  which one to edit.\n- 'approve': Send authorization belongs to the user, so this action needs a\n  message that arrived after the drafts were queued and explicitly says to\n  approve or send them. A message from before the drafts existed cannot\n  authorize them — a request to review them, to approve them later, or to be\n  able to approve from chat means: report that the queue is awaiting approval\n  and end your turn; the user's next message decides. Once authorized, this\n  moves pending_approval items to 'pending'; they then send in queue order at\n  your account's pace. If\n  target_provider_id is given, approve only that item. Otherwise approve ALL\n  pending_approval items (optionally filtered by action_type).\n  Only touches items already awaiting approval — it does NOT run pending profile\n  lookups or pre-approve resolving rows (those aren't in the approvals UI, so\n  nobody has reviewed them; they resolve on their own schedule and, if the\n  user's settings gate the action, surface for approval once resolved).\n  From account-level chat an approve-all is rejected unless task_id names the\n  campaign — it must not fire every campaign's drafts into sending at once.\n- 'cancel': Cancel a queued item. Pass target_provider_id to cancel that one\n  person or post — every queued action for them — or target_identifier to cancel\n  a resolving row that has no pid yet. To cancel the ENTIRE pending\n  queue — which drops drafts the user\n  already approved — you must pass\n  cancel_all=True; an unscoped cancel without it is rejected (an action_type\n  or node_id filter alone is still a bulk cancel and also needs cancel_all=True).\n  Narrow a cancel_all to one flow stage with node_id (e.g. restart only the m2\n  messages without touching m3) — the only way to separate two stages that share\n  an action_type. From account-level chat a cancel_all is rejected unless task_id\n  names the campaign to cancel — it must not clear every campaign's queue at once.\n- 'pause': Pause the queue (stops sending, keeps items queued). Pass resume_at\n  to schedule an automatic resume (\"pause while I'm on vacation, resume July 20\");\n  without it the pause is indefinite and only an explicit 'resume' restarts sending.\n- 'resume': Resume the queue (pending items drain in queue order at your account's pace)"New value: +"One of:\n- 'status': Get full queue details (pending/sent/failed items with names and times).\n  The `pending_items` / `pending_approval_items` / `failed_items` lists cap at 50\n  each, each with a matching `*_truncated` flag — when a list's flag is True, more\n  rows exist past this page; pass `offset` (offset += 50) to read them. Each\n  `failed_items` row carries `last_error`, the reason that send failed — read it to\n  answer \"why wasn't X sent?\". `pending_approval_items` rows also carry `last_error`\n  when the row was held for a reason beyond plain approval gating (e.g. the\n  resolver's name-mismatch hold). Queued post comments and reactions carry `post_url`\n  and a `post_text` excerpt of the post the action targets, so you can tell which\n  post a queued comment is on; `post_text_truncated` True means the target post ran\n  longer than the excerpt shown. All four lists share one field shape; a\n  `resolving_items` row (profile not yet resolved) has a blank `target_provider_id`\n  and its `message` is the copy that will send once it resolves — edit or cancel it\n  by its `target_identifier`. Every `pending_items` / `resolving_items` row carries\n  `projected_send_day` + `projected_send_time` (a resolving row's is its projected\n  lookup time, or its projected send time once it's a resolve-then-send) and a\n  `queue_position` — the row's place in the one ordered lookup+send timeline, so the\n  two lists interleave into what actually fires next. The top-level `cancelled_by_kind` maps each cancel\n  cause to its count (`recipient_replied`, `task_deleted`, `auto_shelved`, …;\n  pre-taxonomy rows under `unknown`) — read it to answer \"how much outreach was\n  cancelled, and why?\".\n- 'update': Update a queued item's message text. Name the item by\n  target_provider_id (a pending row's pid) OR, for a resolving row that has no\n  pid yet, by target_identifier (its URL/slug, shown on the row). Use this to\n  edit a queued message — including on resolving rows, which still hold the\n  message that will send once their profile resolves. When a target has more\n  than one queued action — a post with both a comment and a reaction, or a\n  person with a connection request and a follow — also pass action_type to name\n  which one to edit.\n- 'approve': Send authorization belongs to the user, so this action needs a\n  message that arrived after the drafts were queued and explicitly says to\n  approve or send them. A message from before the drafts existed cannot\n  authorize them — a request to review them, to approve them later, or to be\n  able to approve from chat means: report that the queue is awaiting approval\n  and end your turn; the user's next message decides. Once authorized, this\n  moves pending_approval items to 'pending'; they then send in queue order at\n  your account's pace. If\n  target_provider_id is given, approve only that item. Otherwise approve ALL\n  pending_approval items (optionally filtered by action_type).\n  Only touches items already awaiting approval — it does NOT run pending profile\n  lookups or pre-approve resolving rows (those aren't in the approvals UI, so\n  nobody has reviewed them; they resolve on their own schedule and, if the\n  user's settings gate the action, surface for approval once resolved).\n  From account-level chat an approve-all is rejected unless agent_id names the\n  campaign — it must not fire every campaign's drafts into sending at once.\n- 'cancel': Cancel a queued item. Pass target_provider_id to cancel that one\n  person or post — every queued action for them — or target_identifier to cancel\n  a resolving row that has no pid yet. To cancel the ENTIRE pending\n  queue — which drops drafts the user\n  already approved — you must pass\n  cancel_all=True; an unscoped cancel without it is rejected (an action_type\n  or node_id filter alone is still a bulk cancel and also needs cancel_all=True).\n  Narrow a cancel_all to one flow stage with node_id (e.g. restart only the m2\n  messages without touching m3) — the only way to separate two stages that share\n  an action_type. From account-level chat a cancel_all is rejected unless agent_id\n  names the campaign to cancel — it must not clear every campaign's queue at once.\n- 'pause': Pause the queue (stops sending, keeps items queued). Pass resume_at\n  to schedule an automatic resume (\"pause while I'm on vacation, resume July 20\");\n  without it the pause is indefinite and only an explicit 'resume' restarts sending.\n- 'resume': Resume the queue (pending items drain in queue order at your account's pace)"
    • addedInput schema / properties / agent_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "For 'cancel' and 'approve' — scope a bulk cancel_all / approve-all to one\n    campaign's queue. Required from account-level chat (no active agent), where an\n    unscoped bulk cancel or approve is rejected; call list_agents to get the id."
+}
    • changedInput schema / properties / as_teammate / description
      Previous value: -"Act on a consented teammate's queue instead of your own — pass\ntheir email. Covers approve / cancel / update / status; pause and resume\n(account-wide controls) are not available on a teammate's behalf. A bulk\napprove-all / cancel_all must name one of the teammate's campaigns via\ntask_id. Gated on that teammate's act-on-behalf setting; a teammate who\nhasn't granted it is rejected. Omit for your own."New value: +"Act on a consented teammate's queue instead of your own — pass\ntheir email. Covers approve / cancel / update / status; pause and resume\n(account-wide controls) are not available on a teammate's behalf. A bulk\napprove-all / cancel_all must name one of the teammate's campaigns via\nagent_id. Gated on that teammate's act-on-behalf setting; a teammate who\nhasn't granted it is rejected. Omit for your own."
    • removedInput schema / properties / task_id
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "For 'cancel' and 'approve' — scope a bulk cancel_all / approve-all to one\n    campaign's queue. Required from account-level chat (no active task), where an\n    unscoped bulk cancel or approve is rejected; call list_agents to get the id."
-}
  2. Changed1 schema field changed
    • changedInput schema / properties / task_id / description
      Previous value: -"For 'cancel' and 'approve' — scope a bulk cancel_all / approve-all to one\n    campaign's queue. Required from account-level chat (no active task), where an\n    unscoped bulk cancel or approve is rejected; call list_tasks to get the id."New value: +"For 'cancel' and 'approve' — scope a bulk cancel_all / approve-all to one\n    campaign's queue. Required from account-level chat (no active task), where an\n    unscoped bulk cancel or approve is rejected; call list_agents to get the id."
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true; the description adds substantial behavior beyond that: randomized human-like send intervals, per-user activity-window enforcement, account-wide rate-limit pacing, the cancel_all guard ('Guards against silently tearing down the whole campaign'), approve authorization timing ('needs a message that arrived after the drafts were queued'), and as_teammate permission gating. Nothing contradicts the annotations.

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 description is front-loaded with purpose and is well-blocked by action, but it is long and contains noticeable redundancy: the account-level chat rejection rule appears in the summary, the 'approve' action, and the 'cancel' action; resolving-row behavior appears in both the summary and the 'status' action. The complexity justifies much of the length, but tighter deduplication would help.

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?

With no output schema, the description carries the full burden of explaining return values and does so thoroughly: 50-item list caps with *_truncated flags, last_error on failed items, projected_send_day/time and queue_position interleaving, cancelled_by_kind mapping, and scoping/authorization edge cases. Nothing needed for correct invocation 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%, setting a baseline of 3. The description adds value above the schema by explaining the queue model (activity window, pacing, pre-send stages) and the cross-parameter relationships (why agent_id is required for account-level cancels, why node_id exists when action_type is shared across stages, and how target_identifier substitutes for target_provider_id on resolving rows). This interpretive context moves it above baseline.

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 states a specific verb+resource ('Manage the LinkedIn outbound queue') and goes well beyond a tautology by explaining what the queue is (pre-send LinkedIn actions sent at randomized intervals). It explicitly differentiates itself from siblings: 'The queue only knows the pre-send stages — for a prospect's full lifecycle... read tracking items with query_prospects,' and it is clearly distinct from manage_email_outreach_queue by domain.

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?

Provides explicit when-to-use guidance ('Use this tool to check status, update/cancel items, or pause/resume the queue') and an explicit when-not-to-use with a named alternative (query_prospects for post-send lifecycle). It also covers contextual scoping rules: agent vs account-level chat behavior, bulk-operation restrictions, and teammate act-on-behalf limits.

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

All Sliq toolsInspect
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