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

Annotations already fully cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower. The description still adds real value beyond them: simulation 'sends nothing and uses current facts, not predicted behavior', and emailPreview renders a step 'as review will, before the audience is prepared' — genuine behavioral context.

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?

It is front-loaded with the core purpose and every clause carries information with no filler. The semicolon-separated parenthetical style makes it a dense wall of text that is harder to parse than ideal, but nothing is wasted.

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 10-action multiplexer with no output schema and only a generic payload object, the description is substantially complete on inputs and behavior. It does not describe return values, which would help an 'inspect' tool, but the safety profile is fully carried by annotations.

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 coverage is only 50% and payload is a free-form object, so the description carries most of the burden — and it does, mapping flowId, cursor, email/status filters, expectedRevision, memberId, stepId, targetVersion, targetStepId, and enrollmentIds to specific actions. Only the plain 'list' action is left without parameter detail.

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 states a specific verb ('Inspect') and resource ('visual sequences'/'email sequences') and enumerates the full action set (list, get, enrollments, history, audienceStatus, preview, emailPreview, simulationAudience, simulate, previewMigration). It lets an agent distinguish the read/inspect multiplexer from write siblings like edit_email_sequence and activate_email_sequence, though it never explicitly contrasts them.

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 gives action-level context (e.g. 'Simulation sends nothing and uses current facts, not predicted behavior') and points to a workflow guide resource, so usage is implied. But it never states when to use this tool over siblings such as inspect_email_experiment or edit_email_sequence, and there are no explicit exclusions.

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