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

Annotations already flag this as destructive, non-idempotent and open-world, and the description adds meaningful context on top: the approval gate, the preview/confirm requirement, and the fact that a migrate call uses a 'fresh previewMigration reviewHash and stable requestId', which tempers the non-idempotent hint. It also confirms delivery/consent safeguards stay in force, though it never spells out what is actually destroyed or the blast radius of each action.

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?

Front-loaded with the approval condition, then the four action variants, then the confirmation rule and the guide pointer — a logical order with little filler. It is dense and compressed into a small number of long clauses, which slightly hurts scannability.

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 high-risk multi-action mutation with no output schema, the description covers the approval prerequisite, the preview-before-confirm discipline, safeguard guarantees, and points to the workflow guide resource. The gaps are per-action guardrails (what each action irreversibly changes) rather than anything missing about calling it.

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?

With schema coverage at 67% and `payload` being an open free-form object, the description carries real weight by naming the significant keys (flowId, expectedRevision, reviewHash, expectedVersion, expectedCount, requestId, cursor) and tying reviewHash/requestId to specific actions. It still leaves the exact per-action payload contract partially inferential.

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 names four concrete operations (activate a reviewed flow, resume a paused flow, startAudience, migrate paused enrollments) mapped to the `action` enum, so the resource and verbs are unambiguous. It does not, however, explicitly differentiate itself from adjacent siblings like edit_email_sequence, inspect_email_sequence, or send_email_campaign.

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 a real precondition ('With the organizer's explicit approval') and an operational rule ('Show the exact version, emails, people and timing before confirmation'), which implies when this tool is appropriate. But no alternative tool is ever named, and there is no guidance on when to choose activate vs resume vs startAudience vs migrate beyond the one-line enumeration.

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