Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Manage Email Outreach Queue

manage_email_outreach_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 recipient_email reaches them in any agent. The next send time and per-mailbox usage stay account-wide (the send rate is per-mailbox).

For pausing/resuming the campaign, use update_agent to set the agent status to 'paused' or 'active' instead. Dict with action result and current queue status

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoFor 'update' — new body text.
actionYesOne of: - 'status': Get full queue details (pending/sent/failed items). The `pending_items` / `pending_approval_items` lists cap at 50 each, each with a `pending_truncated` / `pending_approval_truncated` flag — when a list's flag is True, pass `offset` (offset += 50) to read the next page. Each item carries the `mailbox` it sends from; the account-level `mailboxes` list gives each mailbox's remaining daily headroom. 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': Edit a queued email's subject and/or body. Requires recipient_email. Pass subject and/or body to change — no cancel-and-re-queue needed. Send order is derived, not per-row scheduled; to pause or resume the campaign use update_agent (see the note above). - '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: if recipient_email is given, approve only that item, otherwise approve ALL pending_approval items. 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 email. Pass recipient_email to cancel that one person. 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. 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.
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.).
subjectNoFor 'update' — new subject line.
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.
cancel_allNoFor 'cancel' only — confirm a queue-wide cancel when no recipient_email is given. Guards against silently tearing down the whole campaign.
as_teammateNoAct on a consented teammate's email queue instead of your own — pass their email. Covers approve / cancel / update / status; 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.
recipient_emailNoFor 'update', 'approve', and 'cancel' — target a specific recipient. Leave empty to apply to all items (not valid for 'update'; for 'cancel', requires cancel_all=True).

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). The\n  `pending_items` / `pending_approval_items` lists cap at 50 each, each\n  with a `pending_truncated` / `pending_approval_truncated` flag — when a\n  list's flag is True, pass `offset` (offset += 50) to read the next page.\n  Each item carries the `mailbox` it sends from; the account-level\n  `mailboxes` list gives each mailbox's remaining daily headroom. The\n  top-level `cancelled_by_kind` maps each cancel cause to its count\n  (`recipient_replied`, `task_deleted`, `auto_shelved`, …; pre-taxonomy\n  rows under `unknown`) — read it to answer \"how much outreach was\n  cancelled, and why?\".\n- 'update': Edit a queued email's subject and/or body. Requires recipient_email.\n  Pass subject and/or body to change — no cancel-and-re-queue needed. Send order\n  is derived, not per-row scheduled; to pause or resume the campaign use\n  update_agent (see the note above).\n- 'approve': Send authorization belongs to the user, so this action\n  needs a message that arrived after the drafts were queued and\n  explicitly says to approve or send them. A message from before the\n  drafts existed cannot authorize them — a request to review them,\n  to approve them later, or to be able to approve from chat means:\n  report that the queue is awaiting approval and end your turn; the\n  user's next message decides. Once authorized: if recipient_email\n  is given, approve only that item, otherwise approve ALL\n  pending_approval items. From account-level chat an approve-all is\n  rejected unless task_id names the campaign — it must not fire\n  every campaign's drafts into sending at once.\n- 'cancel': Cancel a queued email. Pass recipient_email to cancel that one\n  person. To cancel the ENTIRE pending queue — which drops drafts the user\n  already approved — you must pass\n  cancel_all=True; an unscoped cancel without it is rejected. From\n  account-level chat a cancel_all is rejected unless task_id names the campaign\n  to cancel — it must not clear every campaign's queue at once."New value: +"One of:\n- 'status': Get full queue details (pending/sent/failed items). The\n  `pending_items` / `pending_approval_items` lists cap at 50 each, each\n  with a `pending_truncated` / `pending_approval_truncated` flag — when a\n  list's flag is True, pass `offset` (offset += 50) to read the next page.\n  Each item carries the `mailbox` it sends from; the account-level\n  `mailboxes` list gives each mailbox's remaining daily headroom. The\n  top-level `cancelled_by_kind` maps each cancel cause to its count\n  (`recipient_replied`, `task_deleted`, `auto_shelved`, …; pre-taxonomy\n  rows under `unknown`) — read it to answer \"how much outreach was\n  cancelled, and why?\".\n- 'update': Edit a queued email's subject and/or body. Requires recipient_email.\n  Pass subject and/or body to change — no cancel-and-re-queue needed. Send order\n  is derived, not per-row scheduled; to pause or resume the campaign use\n  update_agent (see the note above).\n- 'approve': Send authorization belongs to the user, so this action\n  needs a message that arrived after the drafts were queued and\n  explicitly says to approve or send them. A message from before the\n  drafts existed cannot authorize them — a request to review them,\n  to approve them later, or to be able to approve from chat means:\n  report that the queue is awaiting approval and end your turn; the\n  user's next message decides. Once authorized: if recipient_email\n  is given, approve only that item, otherwise approve ALL\n  pending_approval items. From account-level chat an approve-all is\n  rejected unless agent_id names the campaign — it must not fire\n  every campaign's drafts into sending at once.\n- 'cancel': Cancel a queued email. Pass recipient_email to cancel that one\n  person. To cancel the ENTIRE pending queue — which drops drafts the user\n  already approved — you must pass\n  cancel_all=True; an unscoped cancel without it is rejected. From\n  account-level chat a cancel_all is rejected unless agent_id names the campaign\n  to cancel — it must not clear every campaign's queue at once."
    • 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 email queue instead of your own —\npass their email. Covers approve / cancel / update / status; 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 email queue instead of your own —\npass their email. Covers approve / cancel / update / status; 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. Changed2 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"One of:\n- 'status': Get full queue details (pending/sent/failed items). The\n  `pending_items` / `pending_approval_items` lists cap at 50 each, each\n  with a `pending_truncated` / `pending_approval_truncated` flag — when a\n  list's flag is True, pass `offset` (offset += 50) to read the next page.\n  Each item carries the `mailbox` it sends from; the account-level\n  `mailboxes` list gives each mailbox's remaining daily headroom. The\n  top-level `cancelled_by_kind` maps each cancel cause to its count\n  (`recipient_replied`, `task_deleted`, `auto_shelved`, …; pre-taxonomy\n  rows under `unknown`) — read it to answer \"how much outreach was\n  cancelled, and why?\".\n- 'update': Edit a queued email's subject and/or body. Requires recipient_email.\n  Pass subject and/or body to change — no cancel-and-re-queue needed. Send order\n  is derived, not per-row scheduled; to pause or resume the campaign use\n  update_task (see the note above).\n- 'approve': Send authorization belongs to the user, so this action\n  needs a message that arrived after the drafts were queued and\n  explicitly says to approve or send them. A message from before the\n  drafts existed cannot authorize them — a request to review them,\n  to approve them later, or to be able to approve from chat means:\n  report that the queue is awaiting approval and end your turn; the\n  user's next message decides. Once authorized: if recipient_email\n  is given, approve only that item, otherwise approve ALL\n  pending_approval items. From account-level chat an approve-all is\n  rejected unless task_id names the campaign — it must not fire\n  every campaign's drafts into sending at once.\n- 'cancel': Cancel a queued email. Pass recipient_email to cancel that one\n  person. To cancel the ENTIRE pending queue — which drops drafts the user\n  already approved — you must pass\n  cancel_all=True; an unscoped cancel without it is rejected. From\n  account-level chat a cancel_all is rejected unless task_id names the campaign\n  to cancel — it must not clear every campaign's queue at once."New value: +"One of:\n- 'status': Get full queue details (pending/sent/failed items). The\n  `pending_items` / `pending_approval_items` lists cap at 50 each, each\n  with a `pending_truncated` / `pending_approval_truncated` flag — when a\n  list's flag is True, pass `offset` (offset += 50) to read the next page.\n  Each item carries the `mailbox` it sends from; the account-level\n  `mailboxes` list gives each mailbox's remaining daily headroom. The\n  top-level `cancelled_by_kind` maps each cancel cause to its count\n  (`recipient_replied`, `task_deleted`, `auto_shelved`, …; pre-taxonomy\n  rows under `unknown`) — read it to answer \"how much outreach was\n  cancelled, and why?\".\n- 'update': Edit a queued email's subject and/or body. Requires recipient_email.\n  Pass subject and/or body to change — no cancel-and-re-queue needed. Send order\n  is derived, not per-row scheduled; to pause or resume the campaign use\n  update_agent (see the note above).\n- 'approve': Send authorization belongs to the user, so this action\n  needs a message that arrived after the drafts were queued and\n  explicitly says to approve or send them. A message from before the\n  drafts existed cannot authorize them — a request to review them,\n  to approve them later, or to be able to approve from chat means:\n  report that the queue is awaiting approval and end your turn; the\n  user's next message decides. Once authorized: if recipient_email\n  is given, approve only that item, otherwise approve ALL\n  pending_approval items. From account-level chat an approve-all is\n  rejected unless task_id names the campaign — it must not fire\n  every campaign's drafts into sending at once.\n- 'cancel': Cancel a queued email. Pass recipient_email to cancel that one\n  person. To cancel the ENTIRE pending queue — which drops drafts the user\n  already approved — you must pass\n  cancel_all=True; an unscoped cancel without it is rejected. From\n  account-level chat a cancel_all is rejected unless task_id names the campaign\n  to cancel — it must not clear every campaign's queue at once."
    • 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

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses important behaviors: staggered send timing, cancel-all dropping already-approved drafts, approval requiring explicit authorization arriving after drafts were queued, per-mailbox rate limits, and pagination truncation behavior. No contradiction with annotations exists.

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?

The description is long, but the length is warranted for an 8-parameter tool with destructive and account-wide behavior. Major constraints are front-loaded in the summary, and action-specific detail is organized in the action enum. It could be tightened with bullet formatting, but every sentence carries meaningful guidance.

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 complex, potentially destructive tool with no output schema, the description covers all critical context: authorization requirements, account vs. agent scope, cancel guards, pagination, mailbox headroom, return content, and the alternative tool for pausing/resuming. Nothing an agent needs to call it safely 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, but the description adds cross-parameter semantics: cancel_all is required for unscoped cancels, agent_id scopes account-level bulk actions, recipient_email targets a single person across any agent, and offset uses 'offset += 50' as a pagination recipe. These relationships go beyond individual schema property descriptions.

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 and resource: 'Manage the email outreach queue' and enumerates the concrete operations: 'check status, update/cancel items, or approve pending items.' It also distinguishes itself from the closely related sibling update_agent by explicitly routing pause/resume behavior to update_agent instead.

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?

The description gives explicit when-to-use context: bulk operations scope to the current agent's queue inside an agent vs. the whole account from account-level chat, account-level cancel_all/approve-all are rejected unless agent_id names the campaign, and pausing/resuming should use update_agent. These exclusions and alternatives leave little to inference.

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