Spaces by Peakflo

workflow_execution_get_steps

Read-only

Get steps of a specific workflow execution to diagnose failures or missing progress.

Use this when a run fails, stays PENDING/RUNNING without progress, or workflow_run_wait returns an unchanged status. Inspect steps before waiting again or assuming a queue problem. Read failed-step errors in stepOutput, repeated attempts for the same node, and timing gaps. PENDING can include retries with backoff even after earlier steps completed. Zero steps alone does not prove worker slots are exhausted. Diagnose the existing execution; do not start a duplicate run to investigate it.

Returns detailed step information including:

Step name and node ID
Status and timing (startedAt, completedAt)
Input data (processData)
Output data (stepOutput)
Token usage
Ordinal position in the execution

Only main workflow steps are returned at the top level. Each main step includes its child tool, verification, write, and recovery substeps in chronological order.

Pagination (optional):

limit: Maximum number of steps to return. When omitted, all steps are returned.
offset: Number of steps to skip (default: 0). Only used when limit is provided.

When pagination is used, the response includes totalSteps (total count of all main steps) to help with subsequent page requests.

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": {
      "executionId": "<executionId>"
    },
    "name": "workflow_execution_get_steps"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of steps to return. When omitted, all steps are returned.
`offset`	No	Number of steps to skip (default: 0). Only used when limit is provided.
`executionId`	Yes	The execution ID to get steps for
`substepLimit`	No	Maximum child details per main step (default: 100, max: 500)
`substepOffset`	No	Child details to skip for each main step (default: 0)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnlyHint/destructiveHint=false, but the description adds real diagnostic behavior: PENDING can include retries with backoff even after earlier steps completed, and zero steps alone does not prove worker slots are exhausted. With no output schema present, its enumeration of returned fields (status, timing, processData, stepOutput, token usage, ordinal) and the main-step/substep nesting also carries the return-value burden.

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?

The structure is strong: purpose first, diagnostic guidance second, return shape third, pagination last. It is longer than needed, however — the pagination bullets largely restate the schema's own parameter descriptions, which is the one place sentences do not earn their place.

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 five parameters, no output schema, and a hierarchical return shape, the description covers everything an agent needs: what triggers a call, what comes back at top level versus substep level, and how paging behaves. No material gap remains for correct invocation and interpretation.

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 limit/offset/executionId are already documented; the description adds meaning by stating that paginated responses include totalSteps to drive subsequent pages, which the schema does not say. It omits substepLimit and substepOffset entirely from the narrative despite describing substeps, leaving those two parameters to 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 opens with a specific verb and resource ('Get steps of a specific workflow execution') and immediately binds it to a purpose ('to diagnose failures or missing progress'). It is clearly distinguishable from siblings such as workflow_execution_list (listing runs) and workflow_run_wait (waiting on a run), which it names directly.

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?

It gives explicit trigger conditions — run failed, stuck PENDING/RUNNING, or workflow_run_wait returning an unchanged status — plus an explicit sequencing instruction ('inspect steps before waiting again') and an explicit exclusion ('do not start a duplicate run to investigate it'). This is the when/when-not/alternative pattern at full strength.

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

All Spaces by Peakflo 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.