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

Annotations only declare write/destructive/openWorld; the description adds the real behavior: the draft keeps evolving while published runs stay frozen until the next publish, publishing does not execute the flow, and runOnPublish evals will start a run that spends credit (with an instruction to surface that to the user). It also discloses the 'needs_confirmation' return path, which is beyond anything the annotations carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The snapshot definition is front-loaded in the first clause and every subsequent sentence carries distinct load-bearing information: consumers of the published version, draft/published divergence, the no-run clarification, credit-spending evals, and the publish precondition. No filler.

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

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

For a state-mutating tool with no output schema, the description covers the lifecycle semantics, side effects (eval runs and credit spend), the confirmation flow, and prerequisites. Nothing material an agent needs before calling it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the schema already documents note, version retagging, workspace defaulting, and the approvalId provenance, so the description adds little parameter-level meaning. Its only addition is the reference to 'needs_confirmation', which is already tied back to approvalId in the schema itself. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a precise verb and resource — 'Snapshots the flow's current DRAFT as a named published version' — and immediately distinguishes this from nearby siblings by naming what consumes the published side (workbench_flows_schedule, workbench_flows_share_create, public-API runs, published-stage evals). An agent can separate this from workbench_flows_run and workbench_flows_update without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states an explicit precondition and alternative: 'Publish only after the user has tested the draft (workbench_flows_run) or asked for it.' It also clarifies the boundary versus running ('Publishing does NOT run the flow') and versus the draft, which is exactly the when/when-not 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.