Spaces by Peakflo

wf_load_demo_ap_and_ar_data_load-d

Destructive

Run workflow: Load demo AP and AR data. It runs against live connected systems. About this workflow: Parse a vendor, bill or invoice CSV and batch-upsert it into the standard analytics tables via entity_write. Workflow ID: load-demo-ap-and-ar-data-0066f8 Use when the user asks for a real workflow run. Use workflow_test_run to test a saved first version. Next step: call workflow_run_wait if the run is async. If pending persists, call workflow_execution_get_steps with executionId (workflow_execution_list lists runs) to inspect failed steps and retries before waiting again. Limits: send an idempotencyKey that is new for each new request; existing:true means an earlier run, not a run now; the server checks access. Example: {"idempotencyKey":"task-42"}.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "wf_load_demo_ap_and_ar_data_load-d"
  }
}

Input Schema

Name	Required	Description
`async`	No	Return a run handle through Inngest
`taskId`	No	Related task ID
`csvText`	No	Full CSV file contents with a header row
`sessionId`	No	Related session ID
`versionId`	No	Pinned version UUID
`entityType`	No	vendor, bill or invoice
`vendorsCsv`	No	vendors.csv contents; required when entityType is bill (vendor name lookup)
`idempotencyKey`	No	Stable key for the requested run

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description adds real substance on top: it runs against live connected systems, it upserts into the standard analytics tables via entity_write, and it explains idempotency semantics ('send an idempotencyKey that is new for each new request; existing:true means an earlier run, not a run now') plus the server-side access check. That is meaningful behavior beyond what the structured fields convey.

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?

Content is front-loaded: purpose first, then what the workflow does, then when-to-use, next steps, limits, and an example. Every section earns its place, though the Next step sentence packs three follow-up tools and conditions into one dense run-on that would read better split.

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?

For a destructive, open-world workflow with no output schema, the description covers the safety profile, live-system impact, idempotency, and the full follow-up lifecycle. It stops short of saying what a run returns (execution handle vs. final result) and that schema marks zero required params even though entityType and csvText are effectively needed.

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 description coverage is 100%, so the baseline is 3; the description still adds value by explaining the idempotencyKey contract (new key per request, existing:true semantics) and by framing csvText/entityType as the vendor, bill, or invoice CSV being upserted. It does not explain how the async handle differs from a synchronous return, which keeps it from a 5.

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 names a specific verb and resource ('Run workflow: Load demo AP and AR data') and then states concretely what the workflow does: parse a vendor, bill or invoice CSV and batch-upsert it into the standard analytics tables via entity_write. It also pins a Workflow ID, so an agent can distinguish this exact workflow from the many other workflow_* siblings.

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 an explicit positive trigger ('Use when the user asks for a real workflow run') and an explicit exclusion with the alternative named ('Use workflow_test_run to test a saved first version'). It also prescribes the post-call sequence, naming workflow_run_wait, workflow_execution_get_steps, and workflow_execution_list for the async and pending cases.

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.