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 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', 'comment_scope', 'draft_comments', 'fetch_engagers', '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'}. comment_scope is the user's own description of which posts are worth a comment (blank means the built-in criteria only). 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 is 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses substantial behavior: default summary vs. roster drill-down, pagination with offset/limit and truncated flag, the exact URL shape expected by setup_linkedin_monitoring, timezone semantics for run_weekdays, and last_run_at being null before first run. This goes well beyond what annotations alone provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place: core purpose, editing caveat, default behavior, drill-down behavior, paging algorithm, field semantics, and return shapes. It is structured with summary and returns sections, making the volume navigable and front-loading the primary purpose.

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?

Given a read-only tool with no output schema, the description fully compensates by specifying both return dict shapes, all key field meanings, pagination semantics, blank-value conventions for engager fields, and the empty-list case. The parameter schema and readOnlyHint annotations are also complete, so an agent has everything needed to invoke the tool correctly.

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?

The input schema already documents all four parameters with good descriptions (100% coverage), so the baseline is 3. The description adds extra meaning for monitor_id by explaining that its id comes from each summary row, and it clarifies paging behavior for offset/limit with the truncated flag. That enrichment justifies a 4.

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 opens with a specific verb-resource pair: 'Read the LinkedIn post monitors configured on an agent', then enumerates exactly what is returned (mode, schedule, writing instructions, enabled actions). This clearly separates it from sibling tools like setup_linkedin_monitoring, edit_monitor_members, and query_monitored_posts, which have different purposes.

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?

The description gives explicit guidance on when to use the tool: read current config before editing a monitor because setup_linkedin_monitoring overwrites unpassed fields. It also explains when to use the default summary vs. the monitor_id drill-down. It does not explicitly list alternative read tools or when-not-to-use conditions, so it stops short of a 5.

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