Marcora

get_workflow_runs

Read-onlyIdempotent

Inspect workflow run history. Two modes controlled by run_id presence:

Input roles:
- workflow_id: UUID string of the workflow.
- run_id: UUID string. If present → single-run detail with step logs and tool call logs. If absent → paginated list of runs.
- status: list-mode filter. Ignored in single mode.
- page / per_page: list-mode pagination.

Usage patterns:
- When the user asks "did my workflow run?": call with just workflow_id (list mode) and look at items[0].status + items[0].completed_at.
- When the user asks "what did that run do?": call with workflow_id + run_id (single mode) and read _step_logs and _tool_call_logs.
- When troubleshooting failures: filter list mode by status="failed", then pull each detail.
- Each run's `id` is a UUID string. The `link_url` on each run points to its detail page in Marcora.

**Links:** present `link_url` to the user exactly as returned — copy it character for character. Never retype, shorten, or rebuild a link or the IDs inside it.

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": {
      "workflow_id": "<workflow_id>"
    },
    "name": "get_workflow_runs"
  }
}

Input Schema

Name	Required	Description
`page`	No	1-based page number through the run list, which is ordered newest first. Defaults to 1, so you only need it to reach runs older than the first page. Ignored when `run_id` is supplied.
`run_id`	No	UUID of one specific run to inspect in full — its step-by-step logs, tool calls and the agent's messages. Pass it when the user asks what a particular run actually did. Omit it to get the paginated list of runs instead.
`status`	No	Restricts the run list to a single exact status: "pending", "running", "succeeded", "failed" or "skipped". Use "failed" when troubleshooting, or "running" to see whether something is in flight. Ignored when `run_id` is supplied.
`per_page`	No	How many runs to return per page. Defaults to 20 when omitted or when the value is not a positive number; set it low (for example 5) when you only need the most recent few. Ignored when `run_id` is supplied.
`workflow_id`	Yes	UUID of the workflow whose run history you want. Required. It scopes the list of runs; when you also pass `run_id`, the run is looked up by that id alone and this value is not used to filter.

Output Schema

Name	Required	Description
`id`	No	Single-run mode — the run UUID.
`items`	No	List mode only — array of runs (most recent first).
`status`	No	Single-run mode — run status.
`link_url`	No	URL to the run detail page (single-run mode; also present on each list item).
`_step_logs`	No	Single-run mode — per-step execution logs.
`itemsTotal`	No	List mode only — total number of runs.
`_tool_call_logs`	No	Single-run mode — tool call logs.
`workflow_template_id`	No	Single-run mode — parent workflow UUID.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description still adds real behavioral context beyond that: the mode switch driven by run_id, the newest-first ordering of the list, and the strict instruction to reproduce link_url character-for-character rather than rebuilding it. It does not mention error cases or what happens when a run_id is not found, which keeps it below a 5.

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?

Well front-loaded: the two-mode rule is stated first, then roles, then usage patterns, then the link handling caveat. There is some redundancy between the "Input roles" list and the already-verbose schema descriptions, but the formatting makes it scannable rather than wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be enumerated, yet the description usefully names the fields the agent should inspect in each mode (items[0].status, _step_logs, _tool_call_logs) and covers the link-presentation constraint. The only real omission is failure behavior for an invalid or unknown run_id.

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 coverage is 100% and the per-parameter descriptions already explain defaults, ordering, the status vocabulary, and the 'ignored when run_id is supplied' rule. The description's "Input roles" section mostly restates that same information in prose, adding framing rather than new meaning, so baseline 3 applies.

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?

Opens with a specific verb and resource ("Inspect workflow run history") and immediately distinguishes its two operating modes by what controls them (presence of run_id). An agent can tell this apart from get_workflow or list_workflows purely from the description.

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 "Usage patterns" block maps concrete user intents ("did my workflow run?", "what did that run do?", troubleshooting failures) onto exact argument combinations and tells the agent what to read from the result. It also states explicitly that status/page/per_page are ignored in single-run mode, which is genuine when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Marcora tools Inspect

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

Need Help?