Skip to main content
Glama
Sign In

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Get run transcript

get_run_transcript
Read-only

Use this when a run's one-line summary isn't enough (e.g. "why did you skip person X in that run?"). Get a run's id from get_agent_details — each entry in its recent_runs list carries one; this returns the same message parts the web Activity tab renders for that run.

The transcript is paginated over its message parts — a heavy run records many. Page with offset while has_more is true. Dict with run_id, the run's summary message + details, status ('completed'/'failed'), created_at, total_messages (parts in the whole run), returned_messages (parts in this page), offset, has_more, and a messages array (role, content or tool_name/args, created_at) sliced to [offset, offset+limit). Empty messages and total_messages 0 when the run recorded no audit session (e.g. it failed before the agent started).

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": {
      "run_id": "<run_id>"
    },
    "name": "get_run_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax message parts to return (default 100, max 200).
offsetNoNumber of parts to skip from the start of the run (default 0).
run_idYesAn agent-run id — the `id` of a `get_agent_details` `recent_runs` entry (also shown as `(run N)` in the agent's Recent Activity feed).
on_behalf_ofNoA 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / on_behalf_of / description
      Previous value: -"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."New value: +"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."
  2. 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."
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / run_id / description
      Previous value: -"An agent-run id — the `id` of a `get_agent_details` `recent_runs`\nentry (also shown as `(run N)` in the task's Recent Activity feed)."New value: +"An agent-run id — the `id` of a `get_agent_details` `recent_runs`\nentry (also shown as `(run N)` in the agent's Recent Activity feed)."
  4. Changed1 schema field changed
    • changedInput schema / properties / run_id / description
      Previous value: -"An agent-run id — the `id` of a `get_task_details` `recent_runs`\nentry (also shown as `(run N)` in the task's Recent Activity feed)."New value: +"An agent-run id — the `id` of a `get_agent_details` `recent_runs`\nentry (also shown as `(run N)` in the task's Recent Activity feed)."
  5. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint, so the description carries the rest: it discloses that results are paginated over message parts, how to detect more pages, and the edge case where an audit session is absent (empty messages, total_messages 0, e.g. a run that failed before the agent started). It stops short of covering retention, redaction, or any size limits on very heavy runs.

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?

Split into summary and returns blocks, front-loaded with the definition, then the usage trigger, then the id source, then pagination. Every sentence supplies either selection context or an invocation mechanic; nothing is 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?

There is no output schema, but the returns block fully enumerates the response keys (run_id, status, total/returned counts, offset, has_more, messages shape) plus the empty-transcript case. For a read-only, four-parameter tool this is complete enough to call correctly on the first attempt.

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 schema already documents limit, offset, run_id and on_behalf_of. The description still adds provenance for run_id (the id of a get_agent_details recent_runs entry, also shown as '(run N)') and the offset/has_more paging contract, which is real meaning beyond the schema fields.

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 ('Read the transcript of one past background agent run') and immediately scopes the content ('every tool call and reasoning step'). It explicitly contrasts with the one-line summary from get_agent_details, so an agent can distinguish it from that sibling without opening either schema.

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 condition ('when a run's one-line summary isn't enough') with a concrete example question, names the sibling that provides the prerequisite id, and explains the paging loop ('Page with offset while has_more is true'). No alternatives are left to inference.

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