ZeroWidth

Publish a Workbench flow version

workbench_flows_publish

Destructive

Snapshots the flow's current DRAFT as a named published version — the version schedules (workbench_flows_schedule), guest share links (workbench_flows_share_create), public-API runs, and 'published'-stage evals execute. The draft keeps evolving after this; runs on the published side don't change until the next publish. Publishing does NOT run the flow, but any eval set to runOnPublish starts a run (that spends credit — mention it when one exists). Refused when the draft hasn't been run since it last changed: try it first with workbench_flows_run on a few real questions, including one it should decline, and read the answers. May return needs_confirmation.

Input Schema

Name	Required	Description
`note`	No	What changed — a commit message.
`flowId`	Yes	Flow to publish.
`untried`	No	true only when the person asked to publish this draft without trying it first.
`version`	Yes	Version label, e.g. '1.0.0' or '2026-09-04'. Re-using a label retags it to this snapshot.
`workspace`	No	Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
`approvalId`	No	Approval id from a prior needs_confirmation response. Omit on the first call.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 22, 2026

addedInput schema / properties / untried

Added value: +{
+  "description": "true only when the person asked to publish this draft without trying it first.",
+  "type": "boolean"
+}

First observedOct 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations flag destructive=true, but the description goes well past that: it explains that the draft keeps evolving while the published snapshot stays frozen, that publishing does NOT execute the flow, that runOnPublish evals spend credit, that refusal occurs for an untried draft, and that a `needs_confirmation` response is possible. These are exactly the side effects an agent must know before invoking a publish.

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?

Front-loaded with the core action and effect, then prerequisites and side effects. Dense with parentheticals (e.g., the credit-spend aside) which slightly reduce scannability, but nearly every clause carries actionable information.

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?

For a destructive, open-world mutation with no output schema, the description covers preconditions, non-obvious side effects, the confirmation flow, and the refusal path. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so all six parameters are documented in the schema, including note, untried, version retagging, workspace scoping, and approvalId. The description adds workflow context around `needs_confirmation` but does not explain the `untried` flag or version label semantics beyond what the schema already says. Baseline 3 is appropriate.

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 ('Snapshots the flow's current DRAFT as a named published version') and immediately clarifies the scope of what that version governs — schedules, share links, public-API runs, evals. An agent can distinguish this from workbench_flows_run, workbench_flows_update, and workbench_flows_schedule without opening any 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?

Explicitly names the precondition (draft must have been run since last change; otherwise refused), prescribes the alternative to try first ('workbench_flows_run on a few real questions, including one it should decline'), and notes the eval cost side effect. This is when/when-not/alternatives guidance in full.

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

All ZeroWidth 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?