Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Edit Monitor Members

edit_monitor_members

add and remove are LinkedIn profile URLs or vanity slugs. A swap is one call (add=[new], remove=[old]). Both forms of one profile (full URL and bare slug) collapse to a single watched member, so re-adding someone already watched is a no-op. The change takes effect on the monitor's next scheduled run.

Use this instead of re-running setup_linkedin_monitoring whenever the user just wants to tweak who's watched ("also watch Bob", "drop Alice"): setup would force re-passing every existing member, and since each watched profile is billed per run, one dropped URL on the re-echo silently stops watching that person. To change schedule, voice, or the action flags, use setup_linkedin_monitoring (members are preserved there when omitted); adding the very first members or resetting the whole list is setup too. Dict with status ('active'), name, members_count, added, removed, unresolved, and message.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addNoLinkedIn profile URLs/slugs to start watching.
nameYesthe monitor to edit (must already exist on this agent).
removeNoLinkedIn profile URLs/slugs to stop watching.
agent_idYesThe agent the monitor lives on.
as_teammateNoEdit a consented teammate's monitor instead of your own — pass their email; agent_id must be one of their agents. Gated on that teammate's act-on-behalf setting; a teammate who hasn't granted it is rejected. Omit for your own.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "The agent the monitor lives on.",
+  "type": "integer"
+}
    • changedInput schema / properties / as_teammate / description
      Previous value: -"Edit a consented teammate's monitor instead of your own — pass\ntheir email; task_id must be one of their tasks. Gated on that teammate's\nact-on-behalf setting; a teammate who hasn't granted it is rejected. Omit\nfor your own."New value: +"Edit a consented teammate's monitor instead of your own — pass\ntheir email; agent_id must be one of their agents. Gated on that teammate's\nact-on-behalf setting; a teammate who hasn't granted it is rejected. Omit\nfor your own."
    • changedInput schema / properties / name / description
      Previous value: -"the monitor to edit (must already exist on this task)."New value: +"the monitor to edit (must already exist on this agent)."
    • removedInput schema / properties / task_id
      Removed value: -{
-  "description": "The task the monitor lives on.",
-  "type": "integer"
-}
    • changedInput schema / required
      Previous value: -[
-  "task_id",
-  "name"
-]New value: +[
+  "agent_id",
+  "name"
+]
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

The description goes well beyond the readOnly/destructive annotations, explaining incrementality, swap semantics, URL/slug collapsing, no-op re-adds, next-scheduled-run timing, and the billing pitfall of re-echoing a dropped URL. This is rich behavioral context that an agent needs to use the tool safely and correctly.

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 well-structured with a summary, behavior details, usage routing, and a returns block. Every sentence carries information; none is filler. The most decision-relevant facts (incremental edits, which tool to choose) are front-loaded.

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 five-parameter tool with no output schema, the description is complete: it documents the return dict's fields, the operational timing, the deduplication behavior, and the sibling tool's role. An agent has everything needed to invoke this tool correctly and to decide when not to.

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 covers all five parameters at 100%, which earns the baseline 3. The description adds meaningful semantic detail for add/remove: they accept full URLs or vanity slugs, a swap is one call, and duplicate forms collapse to one member. These semantics genuinely help parameter construction beyond the schema alone.

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 uses a specific verb phrase ('Add and/or remove watched people') tied to a precise resource ('existing list-mode LinkedIn monitor'), and immediately distinguishes itself from setup_linkedin_monitoring. An agent can tell exactly what this tool does and what it is not.

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 is explicit about when to use this tool instead of setup_linkedin_monitoring, gives concrete user-intent examples ('also watch Bob', 'drop Alice'), and states which cases belong to the alternative tool (changing schedule/voice/action flags, first members, resetting the list). This leaves no ambiguity about routing.

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