Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Get Linkedin Monitors

get_linkedin_monitors
Read-only

Default (no monitor_id): one summary per monitor with members_count (the number of watched LinkedIn profile and company page URLs — list mode only, 0 for network/topic) and members_sample (the first 5 URLs), not the full roster, since a list monitor can watch thousands. To read a monitor's full roster, pass its id (returned on each summary) as monitor_id; that returns the URL list paged by offset/limit with a truncated flag — re-call with offset += limit while truncated. The URLs are in the exact shape setup_linkedin_monitoring takes back. run_weekdays is weekday ints Mon=0 … Sun=6 in the user's timezone. last_run_at is null before the monitor's first run. By default, a dict {'monitors': [{'id', 'name', 'mode', 'is_active', 'members_count', 'members_sample', 'keywords', 'writing_instructions', 'post_filter', 'draft_comments', 'fetch_engagers', 'capture_authors', 'engager_icp', 'engager_instructions', 'run_weekdays', 'recency_days', 'last_run_at'}, ...]} — an empty list if the agent has no monitors. With monitor_id: {'monitor_id', 'name', 'members_count', 'members' (this page's URL list), 'offset', 'limit', 'truncated'}. post_filter is the user's own description of which posts the monitor keeps (blank keeps every post). engager_icp filters who capture collects (blank means everyone) and engager_instructions is what to do with them (blank means take no action); both are blank when fetch_engagers and capture_authors are both off, and both need re-passing when re-arming capture.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax roster URLs per drill-down page (default 200, capped at 200).
offsetNoRoster rows to skip when paging a monitor_id drill-down (default 0).
agent_idYesThe agent whose monitors to read.
monitor_idNoDrill into one monitor's watched-profile roster by its `id`. Omit for the per-monitor summary of all monitors on the agent.
on_behalf_ofNoAn 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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."
+}
  2. Changed4 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "The agent whose monitors to read.",
+  "type": "integer"
+}
    • changedInput schema / properties / monitor_id / description
      Previous value: -"Drill into one monitor's watched-profile roster by its `id`.\nOmit for the per-monitor summary of all monitors on the task."New value: +"Drill into one monitor's watched-profile roster by its `id`.\nOmit for the per-monitor summary of all monitors on the agent."
    • removedInput schema / properties / task_id
      Removed value: -{
-  "description": "The task whose monitors to read.",
-  "type": "integer"
-}
    • changedInput schema / required
      Previous value: -[
-  "task_id"
-]New value: +[
+  "agent_id"
+]
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=true; the description adds substantial non-obvious behavior: the default omits the full roster and returns only members_count/members_sample (first 5) because a list monitor can watch thousands, the truncated flag drives paging, empty list when no monitors, last_run_at null before first run, and run_weekdays isn't disclosed elsewhere. This is exactly the extra context annotations can't carry.

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-loads purpose in the <summary> and separates returns into a distinct block, with no filler sentences. It is dense and slightly long, but with no output schema the returns prose is load-bearing rather than redundant.

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 read tool with 5 parameters, no output schema, and no nested objects, the description supplies both invocation semantics (summary vs. drill-down, paging) and a full return-shape breakdown including blank-field meanings. Nothing an agent needs to call it correctly 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 real meaning: monitor_id is a drill-down key whose value comes from each summary's 'id', offset/limit are a paging pair with a specific retry protocol, and run_weekdays is documented as weekday ints Mon=0…Sun=6 in the user's timezone. It does not add anything for on_behalf_of beyond the schema, keeping it from a 5.

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+resource ("Read the LinkedIn post monitors configured on an agent") and immediately enumerates the fields exposed (mode, schedule, writing instructions, active actions). It implicitly distinguishes itself from the write-path sibling setup_linkedin_monitoring, so an agent can tell read from write 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?

Gives explicit operational guidance: read the current config with this tool before editing because setup_linkedin_monitoring overwrites fields not re-passed, and carry forward unchanged values. It also gives the exact when-to-use condition for monitor_id (full roster drill-down) vs. the default summary, plus the offset += limit retry loop.

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