Spaces by Peakflo

wf_load_policy_documents_load-p

Destructive

Run workflow: Load policy documents. It runs against live connected systems. About this workflow: Chunk, embed and load a policy document into the "Finance policies" datastore. Workflow ID: load-policy-documents-515fcd 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

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": {
      "text": "<text>",
      "fileName": "<fileName>"
    },
    "name": "wf_load_policy_documents_load-p"
  }
}

Input Schema

Name	Required	Description
`text`	Yes	Full document text
`async`	No	Return a run handle through Inngest
`taskId`	No	Related task ID
`fileName`	Yes	Source file name
`sessionId`	No	Related session ID
`versionId`	No	Pinned version UUID
`idempotencyKey`	No	Stable key for the requested run

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026
- addedInput schema / required
```
Added value: +[
+  "text",
+  "fileName"
+]
```
First observedNov 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the safety profile is covered; the description still adds value by warning that the run happens against live connected systems, that the server enforces access, and how idempotency works. It does not spell out precisely what existing datastore content (if any) is replaced or how long the run takes, which keeps it short of 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?

Information is front-loaded (purpose, then workflow detail, then when-to-use, then follow-up steps, then limits, then example) and every sentence carries actionable content. It is dense and slightly run-on, mixing purpose text with operational rules, but nothing is padding.

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 7-parameter, destructive, open-world run tool with no output schema, the description covers purpose, alternatives, async follow-up, and idempotency limits. The remaining gap is the shape of the returned run handle (no output schema exists), which an agent must infer.

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 baseline is 3; the description goes beyond it by explaining idempotencyKey semantics ('new for each new request', 'existing:true means an earlier run, not a run now') and giving a concrete example value. The other six parameters are left to the schema, which is acceptable given full coverage.

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 ('Run workflow: Load policy documents') and immediately explains what the workflow actually does: chunk, embed and load a policy document into the 'Finance policies' datastore. It also gives the workflow ID, so an agent can distinguish this concrete run from the generic workflow_execute or the sibling wf_load_demo_ap_and_ar_data_load-d.

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?

Explicitly says 'Use when the user asks for a real workflow run' and names the alternative: 'Use workflow_test_run to test a saved first version.' It also prescribes the follow-up path (workflow_run_wait for async runs, workflow_execution_get_steps with executionId if pending persists, workflow_execution_list to see runs), which is exactly the routing an agent needs.

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.