Get agent details
get_agent_detailslist_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), except reached.accepted: the people who accepted a connection request
this agent sent them, out of lead_funnel.invited, the people it sent one, as
lead_funnel.accept_rate. lead_funnel.rates {accepted of invited; replied, interested,
meeting_booked of contacted} and lead_funnel.step_rates {interested of replied,
meeting_booked of interested} hold whole percents, null where the base is 0.
lead_funnel.targets holds the LinkedIn target for each rates key, as a whole percent
of the same base, each value null where it doesn't apply: accepted when no connection
request went out, the others when anyone in the funnel is on email or nobody is on
LinkedIn. The lead_funnel's other stage keys count each person once, at their furthest
stage, so together they add up to lead_funnel.prospects.
lead_funnel.removed counts the people removed from the campaign, who stay at the stage
they reached, so it overlaps those keys; list_people with the agent_id and a "removed"
filter of 'removed' lists them.
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.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"agent_id": "<agent_id>"
},
"name": "get_agent_details"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | ID of the agent to load | |
| on_behalf_of | No | 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. | |
| recent_runs_limit | No | How many of the most recent runs to include (default 10, max 50) | |
| recent_runs_offset | No | Runs 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. |