Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Get Agent Details

get_agent_details
Read-only

list_agents returns only one-line summaries — call this to get the full picture for a specific agent. Run-level history is returned here as recent_runs; each entry carries its run id, which you pass to get_run_transcript for that run's full tool-by-tool transcript. Agent-specific operational learnings are returned as a top-level learnings list (managed via append_learning). Dict with agent fields, workspace, learnings, recent_runs, recent_runs_truncated (True when older runs remain past this page of recent_runs), and tracking_summary. When the agent has prospects, tracking_summary.funnel carries the derived outreach rollup the agent workspace shows — per-channel funnels, connection acceptance_rate, reply_rate, and the people-level lead_funnel — so read rates and lead buckets from there rather than deriving them off the raw stage counts. lead_funnel.reached holds the numbers on the funnel's rungs (per rung, everyone who got at least that far); its other stage keys count only the people currently at that stage. mcp_changes lists changes made outside Sliq by the user's or a teammate's MCP clients (such as Claude) calling Sliq tools directly, newest first, one entry per burst of calls to one tool: id, tool_name, client_label (with the teammate's email when a teammate made it), count, first_at, last_at, and latest_arguments (the burst's latest call's arguments). Pass an entry's id as change_id to get_mcp_change_calls to read every call in the burst.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_idYesID of the agent to load
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.
recent_runs_limitNoHow many of the most recent runs to include (default 10, max 50)
recent_runs_offsetNoRuns to skip for paging the recent_runs list (default 0). When `recent_runs_truncated` is True, re-call with recent_runs_offset += recent_runs_limit to page into older runs.

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. Changed3 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "ID of the agent to load",
+  "type": "integer"
+}
    • removedInput schema / properties / task_id
      Removed value: -{
-  "description": "ID of the task to load",
-  "type": "integer"
-}
    • changedInput schema / required
      Previous value: -[
-  "task_id"
-]New value: +[
+  "agent_id"
+]
  3. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description goes beyond that with real behavioral context: pagination via `recent_runs_truncated`/offset, the distinction that `lead_funnel.reached` counts cumulative rungs while other stage keys count current people, and where MCP-originated changes are surfaced. It does not discuss auth or rate limits, but for a read call that is minor.

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 the summary and the sibling differentiation before the long `<returns>` block, which is organized and mostly earns its space given no output schema exists. The returns section is verbose, but the detail is functional rather than padding.

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?

With no output schema, the description carries the full burden of explaining the return shape and does so thoroughly: field inventory, truncation flag, funnel rollup semantics, and cross-tool id routing. Nothing an agent needs to interpret or follow up on the response is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters (including `on_behalf_of` and the paging pair) are already fully documented in the schema. The description adds no parameter-level syntax or semantics beyond what the schema provides, matching the baseline of 3 when the schema does the heavy lifting.

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 and resource ('Load full details for a single agent') and enumerates the payload (workspace, learnings, recent runs, tracking summary). It explicitly contrasts itself with `list_agents`, which returns only one-line summaries, so the agent can select between siblings 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 an explicit trigger ('when the user asks about a specific agent's progress, history, or contents') and names the alternative (`list_agents`) with the condition that selects this tool. The chained-tool routing (run id -> get_run_transcript, change id -> get_mcp_change_calls) further clarifies when to reach for this 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