Skip to main content
Glama
Sign In

Sliq

by com.getsliq
OverviewDiscussionsAdmin

List sent messages

list_sent_messages
Read-only

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_sent_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoCase-insensitive text to find in the message or the recipient's name.
limitNoPage size, at most 200.
offsetNoPage offset. `total` is the count before paging, so the whole tail is reachable.
originNo'sliq' for messages to prospects only, 'imported' for imported conversations only; omit for both.
tag_idNoOnly messages carrying this tag (from list_message_tag_groups); takes precedence over tag_state.
sendersNoIn a shared workspace, the teammate emails (yours included, if wanted) whose messages to list; omit for only your own. An email outside the workspace is dropped; if none remain the list is empty.
positionsNo'first', 'follow_up' and/or 'reply' to narrow by message type; omit for all. A connection-request note is always 'first'.
tag_stateNo'all', 'tagged' (at least one tag in any group) or 'untagged' (no tags; a "No match" result counts as untagged).all
prospect_idNoOnly messages sent to this prospect.
provider_idNoOnly LinkedIn messages sent to this LinkedIn provider id — how to list an imported conversation's messages, which have no prospect_id.
on_behalf_ofNoA teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / on_behalf_of / description
      Previous value: -"An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."New value: +"A teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
    • changedInput schema / properties / senders / description
      Previous value: -"In a shared workspace, the teammate emails (yours included, if wanted) whose\nmessages to list; omit for only your own. A teammate who doesn't share conversations,\nor an email outside the workspace, is dropped; if none remain the list is empty."New value: +"In a shared workspace, the teammate emails (yours included, if wanted) whose\nmessages to list; omit for only your own. An email outside the workspace is dropped; if\nnone remain the list is empty."
  2. Changed1 schema field changed
    • addedInput schema / properties / on_behalf_of
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}
  3. Changed4 schema fields changed
    • addedInput schema / properties / origin
      Added value: +{
+  "anyOf": [
+    {
+      "description": "Whose conversation a sent message belongs to: a Sliq prospect's, or an imported one — a\nLinkedIn conversation the user started with someone who has no prospect row. An origin filter\nis one of these, None for both.",
+      "enum": [
+        "sliq",
+        "imported"
+      ],
+      "title": "Origin",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "'sliq' for messages to prospects only, 'imported' for imported conversations\nonly; omit for both."
+}
    • changedInput schema / properties / positions / anyOf
      Previous value: -[
-  {
-    "items": {
-      "description": "A send's spot in its conversation; a positions filter is a list of these, None for all.\nThe conversation's first outbound send is 'first', a later one sent before the prospect's\nfirst reply is 'follow_up', and any send after that reply is 'reply'. Derived, never stored\nper message.",
-      "enum": [
-        "first",
-        "follow_up",
-        "reply"
-      ],
-      "title": "Position",
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "description": "A send's spot in its conversation; a positions filter is a list of these, None for all.\nThe conversation's first outbound send is 'first', a later one sent before the other person's\nfirst reply is 'follow_up', and any send after that reply is 'reply'. Derived, never stored\nper message.",
+      "enum": [
+        "first",
+        "follow_up",
+        "reply"
+      ],
+      "title": "Position",
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / provider_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only LinkedIn messages sent to this LinkedIn provider id — how to list an\nimported conversation's messages, which have no prospect_id."
+}
    • changedInput schema / properties / q / description
      Previous value: -"Case-insensitive text to find in the message or the prospect's name."New value: +"Case-insensitive text to find in the message or the recipient's name."
  4. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only supply readOnlyHint=true, but the description adds substantial behavior: the default is the caller's own messages only, senders outside the workspace are silently dropped (empty list), and imported conversations behave differently (prospect_id null, reply flags false). It also clarifies that `stats` count prospects once across channels while imported conversations are excluded. It does not discuss permissions or cost beyond on_behalf_of in the schema, so not a full 5.

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?

Front-loaded with a summary and use cases, which is good structure, but the <returns> block is a dense wall covering outcome flags, reply_hours percentiles, and look_up counters. Much of it is necessary given no output schema, yet sentences like the invited/accepted parenthetical and the outcome exception clause are hard to parse in one pass and could be tightened.

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 an 11-parameter read tool with no output schema and only a readOnlyHint, the description supplies everything an agent needs: filter semantics, the sender-default gotcha, paging behavior, and an exhaustive return-value contract. Nothing required to call it correctly or interpret the response 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 schema already carries the baseline; the description still adds meaning by tying filters to purpose (tag_state='untagged' for the tagging workflow) and by tying `limit` to the stats read path. It restates the sender default rather than adding to it, but the limit=1 insight and the stats/filter independence rule are genuine additions beyond the schema.

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 summary states a specific verb+resource (listing every sent message to a prospect or in an imported LinkedIn conversation) and immediately scopes it against alternatives: 'the same list and summary cards as the Analytics → Messages tab.' It also names the siblings it hands off to (correct_message_classification, look_up_imported_people), so an agent can separate it from fetch_linkedin_messages_with_person or get_chat_messages without opening schemas.

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?

Explicit when-to-use cases are enumerated: view untagged messages via tag_state='untagged', read a message's tags across all groups, locate a message to tag with correct_message_classification, or answer reply-rate questions from `stats`. It further states a non-obvious usage rule — that stats follow only `senders` and not the list filters, so `limit=1` is enough to read them — which is exactly the kind of guidance that prevents a mis-call.

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